[ { "provider": "anthropic", "id": "claude-fable-5-1", "display_name": "Claude Fable 5.1", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-fable-5-1" ], "family": "Fable", "generation": "5.1", "description": "For demanding reasoning and long-horizon agentic work", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "lifecycle_docs": "Active (latest)", "release_date": "2026-09-01", "created_at_live": "2026-08-28T00:00:00Z", "knowledge_cutoff": { "reliable": "Jun 2026", "training_data": "Jun 2026" }, "context_window": 1000000, "context_window_note": "1M default, no beta header, standard pricing", "max_output": 128000, "max_output_batch_beta": null, "live_max_input_tokens": 1000000, "live_max_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "thinking": "adaptive (always on)", "capabilities": { "text_input": true, "vision": true, "pdf_input": true, "high_resolution_vision_2576px": true, "tool_use": true, "parallel_tool_use": true, "tool_choice_any_or_tool": false, "strict_tool_use": true, "structured_outputs_json": true, "fine_grained_tool_streaming": true, "thinking_extended_manual_budget": false, "thinking_adaptive": true, "thinking_always_on": true, "thinking_on_by_default": true, "thinking_can_be_disabled": false, "interleaved_thinking": true, "thinking_display_omitted_default": true, "progress_updates_between_tool_calls": true, "effort_parameter": true, "effort_levels": [ "low", "medium", "high", "xhigh", "max" ], "effort_default": "high", "per_message_effort_beta": true, "fast_mode_speed_fast": false, "prompt_caching": true, "prompt_caching_1h_ttl": true, "automatic_caching_top_level_cache_control": true, "min_cacheable_tokens": 512, "batch_api": true, "batch_extended_output_300k_beta": false, "citations": true, "files_api": true, "web_search": true, "web_search_dynamic_filtering": true, "web_fetch": true, "web_fetch_dynamic_filtering": true, "code_execution": true, "code_execution_docs": true, "programmatic_tool_calling": true, "computer_use": true, "computer_use_toolset_ga": true, "browser_use": true, "memory_tool": true, "text_editor_tool": true, "bash_tool": true, "tool_search": true, "advisor_tool": true, "mcp_connector": true, "agent_skills": true, "context_editing_clear_tool_uses": true, "context_editing_clear_thinking": true, "compaction_server_side": true, "compact_on_demand_beta": true, "context_1m_default_no_beta": true, "inference_geo_data_residency": true, "mid_conversation_system_messages": true, "mid_conversation_tool_changes_beta": false, "task_budgets_beta": true, "sampling_params_temperature_top_p_top_k": "rejected with 400 when non-default", "assistant_prefill": false, "priority_tier": false, "zero_data_retention_eligible": false, "tokenizer": "new tokenizer (Claude 4.7+, ~30% more tokens)", "multilingual": true, "latency_class": "Slower", "output_modalities": [ "text" ] }, "live_capabilities": { "batch": { "supported": true }, "citations": { "supported": true }, "code_execution": { "supported": true }, "context_management": { "supported": true, "clear_tool_uses_20250919": { "supported": true }, "clear_thinking_20251015": { "supported": true }, "compact_20260112": { "supported": true } }, "effort": { "supported": true, "low": { "supported": true }, "medium": { "supported": true }, "high": { "supported": true }, "xhigh": { "supported": true }, "max": { "supported": true } }, "image_input": { "supported": true }, "pdf_input": { "supported": true }, "structured_outputs": { "supported": true }, "thinking": { "supported": true, "types": { "enabled": { "supported": false }, "adaptive": { "supported": true } } } }, "tools": [ { "type": "web_search_20260318", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20260209", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20250305", "category": "server", "beta_header": null }, { "type": "web_fetch_20260318", "category": "server", "beta_header": null }, { "type": "web_fetch_20260309", "category": "server", "beta_header": null }, { "type": "web_fetch_20260209", "category": "server", "beta_header": null }, { "type": "web_fetch_20250910", "category": "server", "beta_header": null }, { "type": "code_execution_20260521", "category": "server", "beta_header": null }, { "type": "code_execution_20260120", "category": "server", "beta_header": null }, { "type": "code_execution_20250825", "category": "server", "beta_header": null }, { "type": "tool_search_tool_regex_20251119", "category": "server", "beta_header": null }, { "type": "tool_search_tool_bm25_20251119", "category": "server", "beta_header": null }, { "type": "advisor_20260301", "category": "server", "beta_header": "advisor-tool-2026-03-01" }, { "type": "mcp_toolset", "category": "mcp", "beta_header": "mcp-client-2025-11-20" }, { "type": "memory_20250818", "category": "client", "beta_header": null }, { "type": "bash_20250124", "category": "client", "beta_header": null }, { "type": "text_editor_20250728", "category": "client", "beta_header": null }, { "type": "computer_toolset_20260801", "category": "client", "beta_header": null }, { "type": "browser_toolset_20260801", "category": "client", "beta_header": null }, { "type": "computer_20251124", "category": "client", "beta_header": "computer-use-2025-11-24" } ], "endpoints": [ "POST /v1/messages", "POST /v1/messages/count_tokens", "POST /v1/messages/batches", "GET /v1/models/{model_id}", "Managed Agents (/v1/agents, /v1/sessions) — see managed-agents docs for per-model support" ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "input": 10, "output": 50, "cache_write_5m": 12.5, "cache_write_1h": 20, "cache_read": 0.25, "batch_input": 5.0, "batch_output": 25.0, "batch_discount": 0.5, "long_context_over_200k": "standard pricing (no premium) for 1M-context models", "inference_geo_us_multiplier": 1.1, "priority_tier": "not supported", "cache_read_multiplier": 0.025 }, "rate_limits": { "class": "fable-5.x (shared Fable 5.1 + Fable 5)", "ref": "generated/fragments/rate-limits/anthropic-rate-limits.json", "doc": "https://platform.claude.com/docs/en/api/rate-limits" }, "beta_headers": [ "advisor-tool-2026-03-01", "compact-2026-01-12", "compact-2026-09-04", "computer-use-2025-11-24", "mcp-client-2025-11-20", "mid-conversation-output-config-2026-07-01", "task-budgets-2026-03-13", "thinking-display-updates-2026-08-18" ], "restrictions": { "data_retention": "30-day retention required; not available under ZDR unless authorized", "access": null, "tool_choice": "any/tool return 400", "thinking_disable": "not supported" }, "availability": { "account": "available", "platforms": [ "Claude API", "Amazon Bedrock", "Google Cloud (Vertex AI)", "Microsoft Foundry", "Claude Platform on AWS" ], "cloud_ids": { "bedrock": [ "anthropic.claude-fable-5-1" ], "vertex": "claude-fable-5-1", "foundry": "claude-fable-5-1", "claude_platform_on_aws": "claude-fable-5-1" }, "regions": "Claude API is global by default; inference_geo us/global on 4.6+; Bedrock/Vertex regional endpoints +10%" }, "deprecation": { "state": "Active (latest)", "deprecated_on": null, "retirement": "not sooner than 2027-09-01", "replacement": null }, "discrepancies_live_vs_docs": [ "live created_at 2026-08-28 != documented release 2026-09-01" ], "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 200, "request_note": "GET /v1/models/claude-fable-5-1 -> 200", "messages_probe": { "http_status": 200, "usage": { "input_tokens": 15, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0, "cache_creation": { "ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0 }, "output_tokens": 4, "output_tokens_details": { "thinking_tokens": 0 }, "service_tier": "standard", "inference_geo": "global" }, "stop_reason": "end_turn" } }, "sources": [ { "url": "https://platform.claude.com/docs/en/models/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/models/fable-5-1/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/api/models/list", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/thinking", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/effort", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/prompt-caching", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/context-windows", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-mythos-5-1", "display_name": "Claude Mythos 5.1", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-mythos-5-1" ], "family": "Mythos", "generation": "5.1", "description": "Invite-only frontier model (Project Glasswing)", "status": [ "DOCUMENTED", "ACCOUNT_RESTRICTED", "PREVIEW" ], "lifecycle_docs": "Active (invite only, Project Glasswing)", "release_date": "2026-09-01", "created_at_live": null, "knowledge_cutoff": { "reliable": "Jun 2026", "training_data": "Jun 2026" }, "context_window": 1000000, "context_window_note": "1M default, no beta header, standard pricing", "max_output": 128000, "max_output_batch_beta": null, "live_max_input_tokens": null, "live_max_tokens": null, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "thinking": "adaptive (always on)", "capabilities": { "text_input": true, "vision": true, "pdf_input": true, "high_resolution_vision_2576px": true, "tool_use": true, "parallel_tool_use": true, "tool_choice_any_or_tool": false, "strict_tool_use": true, "structured_outputs_json": true, "fine_grained_tool_streaming": true, "thinking_extended_manual_budget": false, "thinking_adaptive": true, "thinking_always_on": true, "thinking_on_by_default": true, "thinking_can_be_disabled": false, "interleaved_thinking": true, "thinking_display_omitted_default": true, "progress_updates_between_tool_calls": true, "effort_parameter": true, "effort_levels": [ "low", "medium", "high", "xhigh", "max" ], "effort_default": "high", "per_message_effort_beta": true, "fast_mode_speed_fast": false, "prompt_caching": true, "prompt_caching_1h_ttl": true, "automatic_caching_top_level_cache_control": true, "min_cacheable_tokens": 512, "batch_api": true, "batch_extended_output_300k_beta": false, "citations": true, "files_api": true, "web_search": true, "web_search_dynamic_filtering": true, "web_fetch": true, "web_fetch_dynamic_filtering": true, "code_execution": true, "code_execution_docs": true, "programmatic_tool_calling": true, "computer_use": true, "computer_use_toolset_ga": true, "browser_use": true, "memory_tool": true, "text_editor_tool": true, "bash_tool": true, "tool_search": true, "advisor_tool": true, "mcp_connector": true, "agent_skills": true, "context_editing_clear_tool_uses": true, "context_editing_clear_thinking": true, "compaction_server_side": true, "compact_on_demand_beta": true, "context_1m_default_no_beta": true, "inference_geo_data_residency": true, "mid_conversation_system_messages": true, "mid_conversation_tool_changes_beta": false, "task_budgets_beta": true, "sampling_params_temperature_top_p_top_k": "rejected with 400 when non-default", "assistant_prefill": false, "priority_tier": false, "zero_data_retention_eligible": false, "tokenizer": "new tokenizer (Claude 4.7+, ~30% more tokens)", "multilingual": true, "latency_class": "Slower", "output_modalities": [ "text" ] }, "live_capabilities": null, "tools": [ { "type": "web_search_20260318", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20260209", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20250305", "category": "server", "beta_header": null }, { "type": "web_fetch_20260318", "category": "server", "beta_header": null }, { "type": "web_fetch_20260309", "category": "server", "beta_header": null }, { "type": "web_fetch_20260209", "category": "server", "beta_header": null }, { "type": "web_fetch_20250910", "category": "server", "beta_header": null }, { "type": "code_execution_20260521", "category": "server", "beta_header": null }, { "type": "code_execution_20260120", "category": "server", "beta_header": null }, { "type": "code_execution_20250825", "category": "server", "beta_header": null }, { "type": "tool_search_tool_regex_20251119", "category": "server", "beta_header": null }, { "type": "tool_search_tool_bm25_20251119", "category": "server", "beta_header": null }, { "type": "advisor_20260301", "category": "server", "beta_header": "advisor-tool-2026-03-01" }, { "type": "mcp_toolset", "category": "mcp", "beta_header": "mcp-client-2025-11-20" }, { "type": "memory_20250818", "category": "client", "beta_header": null }, { "type": "bash_20250124", "category": "client", "beta_header": null }, { "type": "text_editor_20250728", "category": "client", "beta_header": null }, { "type": "computer_toolset_20260801", "category": "client", "beta_header": null }, { "type": "browser_toolset_20260801", "category": "client", "beta_header": null }, { "type": "computer_20251124", "category": "client", "beta_header": "computer-use-2025-11-24" } ], "endpoints": [ "POST /v1/messages", "POST /v1/messages/count_tokens", "POST /v1/messages/batches", "GET /v1/models/{model_id}", "Managed Agents (/v1/agents, /v1/sessions) — see managed-agents docs for per-model support" ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "input": 10, "output": 50, "cache_write_5m": 12.5, "cache_write_1h": 20, "cache_read": 0.25, "batch_input": 5.0, "batch_output": 25.0, "batch_discount": 0.5, "long_context_over_200k": "standard pricing (no premium) for 1M-context models", "inference_geo_us_multiplier": 1.1, "priority_tier": "not supported", "cache_read_multiplier": 0.025 }, "rate_limits": { "class": "mythos-5.x (shared Mythos 5.1 + Mythos 5; same terms as Fable)", "ref": "generated/fragments/rate-limits/anthropic-rate-limits.json", "doc": "https://platform.claude.com/docs/en/api/rate-limits" }, "beta_headers": [ "advisor-tool-2026-03-01", "compact-2026-01-12", "compact-2026-09-04", "computer-use-2025-11-24", "mcp-client-2025-11-20", "mid-conversation-output-config-2026-07-01", "task-budgets-2026-03-13", "thinking-display-updates-2026-08-18" ], "restrictions": { "data_retention": "30-day retention required; not available under ZDR unless authorized", "access": "invite only (Project Glasswing)", "tool_choice": "any/tool return 400", "thinking_disable": "not supported" }, "availability": { "account": "not visible to our key (404)", "platforms": [ "Claude API", "Amazon Bedrock", "Google Cloud (Vertex AI)", "Microsoft Foundry" ], "cloud_ids": { "bedrock": [ "anthropic.claude-mythos-5-1" ], "vertex": "claude-mythos-5-1", "foundry": "claude-mythos-5-1", "claude_platform_on_aws": null }, "regions": "Claude API is global by default; inference_geo us/global on 4.6+; Bedrock/Vertex regional endpoints +10%" }, "deprecation": { "state": "Active (invite only, Project Glasswing)", "deprecated_on": null, "retirement": "not sooner than 2027-09-01", "replacement": null }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "restricted", "http_status": 404, "request_note": "GET /v1/models/claude-mythos-5-1 -> 404" }, "sources": [ { "url": "https://platform.claude.com/docs/en/models/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/models/mythos-5-1/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/api/models/list", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/thinking", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/effort", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/prompt-caching", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/context-windows", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-fable-5", "display_name": "Claude Fable 5", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-fable-5" ], "family": "Fable", "generation": "5", "description": "Most capable widely released model at launch; access paused then restored 2026-07-01", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "LEGACY" ], "lifecycle_docs": "Active (legacy)", "release_date": "2026-06-09", "created_at_live": "2026-06-07T00:00:00Z", "knowledge_cutoff": { "reliable": "Jan 2026", "training_data": "Jan 2026" }, "context_window": 1000000, "context_window_note": "1M default, no beta header, standard pricing", "max_output": 128000, "max_output_batch_beta": null, "live_max_input_tokens": 1000000, "live_max_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "thinking": "adaptive (always on)", "capabilities": { "text_input": true, "vision": true, "pdf_input": true, "high_resolution_vision_2576px": true, "tool_use": true, "parallel_tool_use": true, "tool_choice_any_or_tool": true, "strict_tool_use": true, "structured_outputs_json": true, "fine_grained_tool_streaming": true, "thinking_extended_manual_budget": false, "thinking_adaptive": true, "thinking_always_on": true, "thinking_on_by_default": true, "thinking_can_be_disabled": false, "interleaved_thinking": true, "thinking_display_omitted_default": true, "progress_updates_between_tool_calls": true, "effort_parameter": true, "effort_levels": [ "low", "medium", "high", "xhigh", "max" ], "effort_default": "high", "per_message_effort_beta": false, "fast_mode_speed_fast": false, "prompt_caching": true, "prompt_caching_1h_ttl": true, "automatic_caching_top_level_cache_control": true, "min_cacheable_tokens": 512, "batch_api": true, "batch_extended_output_300k_beta": false, "citations": true, "files_api": true, "web_search": true, "web_search_dynamic_filtering": true, "web_fetch": true, "web_fetch_dynamic_filtering": true, "code_execution": true, "code_execution_docs": true, "programmatic_tool_calling": true, "computer_use": true, "computer_use_toolset_ga": true, "browser_use": true, "memory_tool": true, "text_editor_tool": true, "bash_tool": true, "tool_search": true, "advisor_tool": true, "mcp_connector": true, "agent_skills": true, "context_editing_clear_tool_uses": true, "context_editing_clear_thinking": true, "compaction_server_side": true, "compact_on_demand_beta": true, "context_1m_default_no_beta": true, "inference_geo_data_residency": true, "mid_conversation_system_messages": true, "mid_conversation_tool_changes_beta": true, "task_budgets_beta": true, "sampling_params_temperature_top_p_top_k": "rejected with 400 when non-default", "assistant_prefill": false, "priority_tier": true, "zero_data_retention_eligible": false, "tokenizer": "new tokenizer (Claude 4.7+, ~30% more tokens)", "multilingual": true, "latency_class": null, "output_modalities": [ "text" ] }, "live_capabilities": { "batch": { "supported": true }, "citations": { "supported": true }, "code_execution": { "supported": true }, "context_management": { "supported": true, "clear_tool_uses_20250919": { "supported": true }, "clear_thinking_20251015": { "supported": true }, "compact_20260112": { "supported": true } }, "effort": { "supported": true, "low": { "supported": true }, "medium": { "supported": true }, "high": { "supported": true }, "xhigh": { "supported": true }, "max": { "supported": true } }, "image_input": { "supported": true }, "pdf_input": { "supported": true }, "structured_outputs": { "supported": true }, "thinking": { "supported": true, "types": { "enabled": { "supported": false }, "adaptive": { "supported": true } } } }, "tools": [ { "type": "web_search_20260318", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20260209", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20250305", "category": "server", "beta_header": null }, { "type": "web_fetch_20260318", "category": "server", "beta_header": null }, { "type": "web_fetch_20260309", "category": "server", "beta_header": null }, { "type": "web_fetch_20260209", "category": "server", "beta_header": null }, { "type": "web_fetch_20250910", "category": "server", "beta_header": null }, { "type": "code_execution_20260521", "category": "server", "beta_header": null }, { "type": "code_execution_20260120", "category": "server", "beta_header": null }, { "type": "code_execution_20250825", "category": "server", "beta_header": null }, { "type": "tool_search_tool_regex_20251119", "category": "server", "beta_header": null }, { "type": "tool_search_tool_bm25_20251119", "category": "server", "beta_header": null }, { "type": "advisor_20260301", "category": "server", "beta_header": "advisor-tool-2026-03-01" }, { "type": "mcp_toolset", "category": "mcp", "beta_header": "mcp-client-2025-11-20" }, { "type": "memory_20250818", "category": "client", "beta_header": null }, { "type": "bash_20250124", "category": "client", "beta_header": null }, { "type": "text_editor_20250728", "category": "client", "beta_header": null }, { "type": "computer_toolset_20260801", "category": "client", "beta_header": null }, { "type": "browser_toolset_20260801", "category": "client", "beta_header": null }, { "type": "computer_20251124", "category": "client", "beta_header": "computer-use-2025-11-24" } ], "endpoints": [ "POST /v1/messages", "POST /v1/messages/count_tokens", "POST /v1/messages/batches", "GET /v1/models/{model_id}", "Managed Agents (/v1/agents, /v1/sessions) — see managed-agents docs for per-model support" ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "input": 10, "output": 50, "cache_write_5m": 12.5, "cache_write_1h": 20, "cache_read": 1.0, "batch_input": 5.0, "batch_output": 25.0, "batch_discount": 0.5, "long_context_over_200k": "standard pricing (no premium) for 1M-context models", "inference_geo_us_multiplier": 1.1, "priority_tier": "same token prices; capacity commitment, no longer sold", "cache_read_multiplier": 0.1 }, "rate_limits": { "class": "fable-5.x (shared Fable 5.1 + Fable 5)", "ref": "generated/fragments/rate-limits/anthropic-rate-limits.json", "doc": "https://platform.claude.com/docs/en/api/rate-limits" }, "beta_headers": [ "advisor-tool-2026-03-01", "compact-2026-01-12", "compact-2026-09-04", "computer-use-2025-11-24", "mcp-client-2025-11-20", "mid-conversation-tool-changes-2026-07-01", "task-budgets-2026-03-13", "thinking-display-updates-2026-08-18" ], "restrictions": { "data_retention": "30-day retention required; not available under ZDR unless authorized", "access": null, "tool_choice": null, "thinking_disable": "not supported" }, "availability": { "account": "available", "platforms": [ "Claude API", "Amazon Bedrock", "Google Cloud (Vertex AI)", "Microsoft Foundry", "Claude Platform on AWS" ], "cloud_ids": { "bedrock": [ "anthropic.claude-fable-5" ], "vertex": "claude-fable-5", "foundry": "claude-fable-5", "claude_platform_on_aws": "claude-fable-5" }, "regions": "Claude API is global by default; inference_geo us/global on 4.6+; Bedrock/Vertex regional endpoints +10%" }, "deprecation": { "state": "Active (legacy)", "deprecated_on": null, "retirement": "not sooner than 2027-06-09", "replacement": null }, "discrepancies_live_vs_docs": [ "live created_at 2026-06-07 != documented release 2026-06-09" ], "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 200, "request_note": "GET /v1/models/claude-fable-5 -> 200" }, "sources": [ { "url": "https://platform.claude.com/docs/en/models/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/models/fable-5/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/api/models/list", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/thinking", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/effort", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/prompt-caching", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/context-windows", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-mythos-5", "display_name": "Claude Mythos 5", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-mythos-5" ], "family": "Mythos", "generation": "5", "description": "Invite-only frontier model (Project Glasswing)", "status": [ "DOCUMENTED", "ACCOUNT_RESTRICTED", "PREVIEW" ], "lifecycle_docs": "Active (invite only, Project Glasswing)", "release_date": "2026-06-09", "created_at_live": null, "knowledge_cutoff": { "reliable": "Jan 2026", "training_data": "Jan 2026" }, "context_window": 1000000, "context_window_note": "1M default, no beta header, standard pricing", "max_output": 128000, "max_output_batch_beta": null, "live_max_input_tokens": null, "live_max_tokens": null, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "thinking": "adaptive (always on)", "capabilities": { "text_input": true, "vision": true, "pdf_input": true, "high_resolution_vision_2576px": true, "tool_use": true, "parallel_tool_use": true, "tool_choice_any_or_tool": true, "strict_tool_use": true, "structured_outputs_json": true, "fine_grained_tool_streaming": true, "thinking_extended_manual_budget": false, "thinking_adaptive": true, "thinking_always_on": true, "thinking_on_by_default": true, "thinking_can_be_disabled": false, "interleaved_thinking": true, "thinking_display_omitted_default": true, "progress_updates_between_tool_calls": false, "effort_parameter": true, "effort_levels": [ "low", "medium", "high", "xhigh", "max" ], "effort_default": "high", "per_message_effort_beta": false, "fast_mode_speed_fast": false, "prompt_caching": true, "prompt_caching_1h_ttl": true, "automatic_caching_top_level_cache_control": true, "min_cacheable_tokens": 512, "batch_api": true, "batch_extended_output_300k_beta": false, "citations": true, "files_api": true, "web_search": true, "web_search_dynamic_filtering": true, "web_fetch": true, "web_fetch_dynamic_filtering": true, "code_execution": true, "code_execution_docs": true, "programmatic_tool_calling": true, "computer_use": true, "computer_use_toolset_ga": true, "browser_use": true, "memory_tool": true, "text_editor_tool": true, "bash_tool": true, "tool_search": true, "advisor_tool": true, "mcp_connector": true, "agent_skills": true, "context_editing_clear_tool_uses": true, "context_editing_clear_thinking": true, "compaction_server_side": true, "compact_on_demand_beta": true, "context_1m_default_no_beta": true, "inference_geo_data_residency": true, "mid_conversation_system_messages": true, "mid_conversation_tool_changes_beta": true, "task_budgets_beta": true, "sampling_params_temperature_top_p_top_k": "rejected with 400 when non-default", "assistant_prefill": false, "priority_tier": false, "zero_data_retention_eligible": false, "tokenizer": "new tokenizer (Claude 4.7+, ~30% more tokens)", "multilingual": true, "latency_class": null, "output_modalities": [ "text" ] }, "live_capabilities": null, "tools": [ { "type": "web_search_20260318", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20260209", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20250305", "category": "server", "beta_header": null }, { "type": "web_fetch_20260318", "category": "server", "beta_header": null }, { "type": "web_fetch_20260309", "category": "server", "beta_header": null }, { "type": "web_fetch_20260209", "category": "server", "beta_header": null }, { "type": "web_fetch_20250910", "category": "server", "beta_header": null }, { "type": "code_execution_20260521", "category": "server", "beta_header": null }, { "type": "code_execution_20260120", "category": "server", "beta_header": null }, { "type": "code_execution_20250825", "category": "server", "beta_header": null }, { "type": "tool_search_tool_regex_20251119", "category": "server", "beta_header": null }, { "type": "tool_search_tool_bm25_20251119", "category": "server", "beta_header": null }, { "type": "advisor_20260301", "category": "server", "beta_header": "advisor-tool-2026-03-01" }, { "type": "mcp_toolset", "category": "mcp", "beta_header": "mcp-client-2025-11-20" }, { "type": "memory_20250818", "category": "client", "beta_header": null }, { "type": "bash_20250124", "category": "client", "beta_header": null }, { "type": "text_editor_20250728", "category": "client", "beta_header": null }, { "type": "computer_toolset_20260801", "category": "client", "beta_header": null }, { "type": "browser_toolset_20260801", "category": "client", "beta_header": null }, { "type": "computer_20251124", "category": "client", "beta_header": "computer-use-2025-11-24" } ], "endpoints": [ "POST /v1/messages", "POST /v1/messages/count_tokens", "POST /v1/messages/batches", "GET /v1/models/{model_id}", "Managed Agents (/v1/agents, /v1/sessions) — see managed-agents docs for per-model support" ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "input": 10, "output": 50, "cache_write_5m": 12.5, "cache_write_1h": 20, "cache_read": 1.0, "batch_input": 5.0, "batch_output": 25.0, "batch_discount": 0.5, "long_context_over_200k": "standard pricing (no premium) for 1M-context models", "inference_geo_us_multiplier": 1.1, "priority_tier": "not supported", "cache_read_multiplier": 0.1 }, "rate_limits": { "class": "mythos-5.x (shared Mythos 5.1 + Mythos 5; same terms as Fable)", "ref": "generated/fragments/rate-limits/anthropic-rate-limits.json", "doc": "https://platform.claude.com/docs/en/api/rate-limits" }, "beta_headers": [ "advisor-tool-2026-03-01", "compact-2026-01-12", "compact-2026-09-04", "computer-use-2025-11-24", "mcp-client-2025-11-20", "mid-conversation-tool-changes-2026-07-01", "task-budgets-2026-03-13" ], "restrictions": { "data_retention": "30-day retention required; not available under ZDR unless authorized", "access": "invite only (Project Glasswing)", "tool_choice": null, "thinking_disable": "not supported" }, "availability": { "account": "not visible to our key (404)", "platforms": [ "Claude API", "Amazon Bedrock", "Google Cloud (Vertex AI)", "Microsoft Foundry" ], "cloud_ids": { "bedrock": [ "anthropic.claude-mythos-5" ], "vertex": "claude-mythos-5", "foundry": "claude-mythos-5", "claude_platform_on_aws": null }, "regions": "Claude API is global by default; inference_geo us/global on 4.6+; Bedrock/Vertex regional endpoints +10%" }, "deprecation": { "state": "Active (invite only, Project Glasswing)", "deprecated_on": null, "retirement": "not sooner than 2027-06-09", "replacement": null }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "restricted", "http_status": 404, "request_note": "GET /v1/models/claude-mythos-5 -> 404" }, "sources": [ { "url": "https://platform.claude.com/docs/en/models/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/models/mythos-5/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/api/models/list", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/thinking", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/effort", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/prompt-caching", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/context-windows", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-mythos-preview", "display_name": "Claude Mythos Preview", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-mythos-preview" ], "family": "Mythos", "generation": "preview", "description": "Gated research preview for defensive cybersecurity (Project Glasswing); migrate to claude-mythos-5", "status": [ "DOCUMENTED", "ACCOUNT_RESTRICTED", "DEPRECATED", "PREVIEW" ], "lifecycle_docs": "Deprecated (invite only)", "release_date": "2026-04-07", "created_at_live": null, "knowledge_cutoff": { "reliable": null, "training_data": null }, "context_window": 1000000, "context_window_note": "1M default, no beta header, standard pricing", "max_output": 128000, "max_output_batch_beta": null, "live_max_input_tokens": null, "live_max_tokens": null, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "thinking": "adaptive", "capabilities": { "text_input": true, "vision": true, "pdf_input": true, "high_resolution_vision_2576px": true, "tool_use": true, "parallel_tool_use": true, "tool_choice_any_or_tool": true, "strict_tool_use": true, "structured_outputs_json": true, "fine_grained_tool_streaming": true, "thinking_extended_manual_budget": false, "thinking_adaptive": true, "thinking_always_on": false, "thinking_on_by_default": false, "thinking_can_be_disabled": true, "interleaved_thinking": true, "thinking_display_omitted_default": true, "progress_updates_between_tool_calls": false, "effort_parameter": true, "effort_levels": [ "low", "medium", "high", "max" ], "effort_default": "high", "per_message_effort_beta": false, "fast_mode_speed_fast": false, "prompt_caching": true, "prompt_caching_1h_ttl": true, "automatic_caching_top_level_cache_control": true, "min_cacheable_tokens": 2048, "batch_api": true, "batch_extended_output_300k_beta": false, "citations": true, "files_api": true, "web_search": true, "web_search_dynamic_filtering": true, "web_fetch": true, "web_fetch_dynamic_filtering": true, "code_execution": true, "code_execution_docs": true, "programmatic_tool_calling": true, "computer_use": false, "computer_use_toolset_ga": false, "browser_use": false, "memory_tool": true, "text_editor_tool": true, "bash_tool": true, "tool_search": true, "advisor_tool": false, "mcp_connector": true, "agent_skills": true, "context_editing_clear_tool_uses": true, "context_editing_clear_thinking": true, "compaction_server_side": true, "compact_on_demand_beta": true, "context_1m_default_no_beta": true, "inference_geo_data_residency": true, "mid_conversation_system_messages": false, "mid_conversation_tool_changes_beta": false, "task_budgets_beta": false, "sampling_params_temperature_top_p_top_k": "rejected with 400 when non-default", "assistant_prefill": "unknown", "priority_tier": false, "zero_data_retention_eligible": true, "tokenizer": "new tokenizer (Claude 4.7+, ~30% more tokens)", "multilingual": true, "latency_class": null, "output_modalities": [ "text" ] }, "live_capabilities": null, "tools": [ { "type": "web_search_20260318", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20260209", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20250305", "category": "server", "beta_header": null }, { "type": "web_fetch_20260318", "category": "server", "beta_header": null }, { "type": "web_fetch_20260309", "category": "server", "beta_header": null }, { "type": "web_fetch_20260209", "category": "server", "beta_header": null }, { "type": "web_fetch_20250910", "category": "server", "beta_header": null }, { "type": "code_execution_20260521", "category": "server", "beta_header": null }, { "type": "code_execution_20260120", "category": "server", "beta_header": null }, { "type": "code_execution_20250825", "category": "server", "beta_header": null }, { "type": "tool_search_tool_regex_20251119", "category": "server", "beta_header": null }, { "type": "tool_search_tool_bm25_20251119", "category": "server", "beta_header": null }, { "type": "mcp_toolset", "category": "mcp", "beta_header": "mcp-client-2025-11-20" }, { "type": "memory_20250818", "category": "client", "beta_header": null }, { "type": "bash_20250124", "category": "client", "beta_header": null }, { "type": "text_editor_20250728", "category": "client", "beta_header": null } ], "endpoints": [ "POST /v1/messages", "POST /v1/messages/count_tokens", "POST /v1/messages/batches", "GET /v1/models/{model_id}", "Managed Agents (/v1/agents, /v1/sessions) — see managed-agents docs for per-model support" ], "pricing": null, "rate_limits": { "class": null, "ref": "generated/fragments/rate-limits/anthropic-rate-limits.json", "doc": "https://platform.claude.com/docs/en/api/rate-limits" }, "beta_headers": [ "compact-2026-01-12", "compact-2026-09-04", "mcp-client-2025-11-20" ], "restrictions": { "data_retention": null, "access": "invite only (Project Glasswing)", "tool_choice": null, "thinking_disable": null }, "availability": { "account": "not visible to our key (404)", "platforms": [ "Claude API", "Amazon Bedrock" ], "cloud_ids": { "bedrock": [ "anthropic.claude-mythos-preview" ], "vertex": null, "foundry": null, "claude_platform_on_aws": null }, "regions": "Claude API is global by default; inference_geo us/global on 4.6+; Bedrock/Vertex regional endpoints +10%" }, "deprecation": { "state": "Deprecated (invite only)", "deprecated_on": "2026-06-09", "retirement": "to be announced (deprecated 2026-06-09)", "replacement": "claude-mythos-5" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "restricted", "http_status": 404, "request_note": "GET /v1/models/claude-mythos-preview -> 404" }, "sources": [ { "url": "https://platform.claude.com/docs/en/models/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/api/models/list", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/thinking", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/effort", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/prompt-caching", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/context-windows", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-opus-5", "display_name": "Claude Opus 5", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-opus-5" ], "family": "Opus", "generation": "5", "description": "For complex agentic coding and enterprise work", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "lifecycle_docs": "Active (latest)", "release_date": "2026-07-24", "created_at_live": "2026-07-24T00:00:00Z", "knowledge_cutoff": { "reliable": "May 2026", "training_data": "May 2026" }, "context_window": 1000000, "context_window_note": "1M default, no beta header, standard pricing", "max_output": 128000, "max_output_batch_beta": 300000, "live_max_input_tokens": 1000000, "live_max_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "thinking": "adaptive (on by default)", "capabilities": { "text_input": true, "vision": true, "pdf_input": true, "high_resolution_vision_2576px": true, "tool_use": true, "parallel_tool_use": true, "tool_choice_any_or_tool": true, "strict_tool_use": true, "structured_outputs_json": true, "fine_grained_tool_streaming": true, "thinking_extended_manual_budget": false, "thinking_adaptive": true, "thinking_always_on": false, "thinking_on_by_default": true, "thinking_can_be_disabled": true, "interleaved_thinking": true, "thinking_display_omitted_default": true, "progress_updates_between_tool_calls": false, "effort_parameter": true, "effort_levels": [ "low", "medium", "high", "xhigh", "max" ], "effort_default": "high", "per_message_effort_beta": true, "fast_mode_speed_fast": true, "prompt_caching": true, "prompt_caching_1h_ttl": true, "automatic_caching_top_level_cache_control": true, "min_cacheable_tokens": 512, "batch_api": true, "batch_extended_output_300k_beta": true, "citations": true, "files_api": true, "web_search": true, "web_search_dynamic_filtering": true, "web_fetch": true, "web_fetch_dynamic_filtering": true, "code_execution": true, "code_execution_docs": true, "programmatic_tool_calling": true, "computer_use": true, "computer_use_toolset_ga": true, "browser_use": true, "memory_tool": true, "text_editor_tool": true, "bash_tool": true, "tool_search": true, "advisor_tool": true, "mcp_connector": true, "agent_skills": true, "context_editing_clear_tool_uses": true, "context_editing_clear_thinking": true, "compaction_server_side": true, "compact_on_demand_beta": true, "context_1m_default_no_beta": true, "inference_geo_data_residency": true, "mid_conversation_system_messages": true, "mid_conversation_tool_changes_beta": true, "task_budgets_beta": true, "sampling_params_temperature_top_p_top_k": "rejected with 400 when non-default", "assistant_prefill": false, "priority_tier": false, "zero_data_retention_eligible": true, "tokenizer": "new tokenizer (Claude 4.7+, ~30% more tokens)", "multilingual": true, "latency_class": "Moderate", "output_modalities": [ "text" ] }, "live_capabilities": { "batch": { "supported": true }, "citations": { "supported": true }, "code_execution": { "supported": true }, "context_management": { "supported": true, "clear_tool_uses_20250919": { "supported": true }, "clear_thinking_20251015": { "supported": true }, "compact_20260112": { "supported": true } }, "effort": { "supported": true, "low": { "supported": true }, "medium": { "supported": true }, "high": { "supported": true }, "xhigh": { "supported": true }, "max": { "supported": true } }, "image_input": { "supported": true }, "pdf_input": { "supported": true }, "structured_outputs": { "supported": true }, "thinking": { "supported": true, "types": { "enabled": { "supported": false }, "adaptive": { "supported": true } } } }, "tools": [ { "type": "web_search_20260318", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20260209", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20250305", "category": "server", "beta_header": null }, { "type": "web_fetch_20260318", "category": "server", "beta_header": null }, { "type": "web_fetch_20260309", "category": "server", "beta_header": null }, { "type": "web_fetch_20260209", "category": "server", "beta_header": null }, { "type": "web_fetch_20250910", "category": "server", "beta_header": null }, { "type": "code_execution_20260521", "category": "server", "beta_header": null }, { "type": "code_execution_20260120", "category": "server", "beta_header": null }, { "type": "code_execution_20250825", "category": "server", "beta_header": null }, { "type": "tool_search_tool_regex_20251119", "category": "server", "beta_header": null }, { "type": "tool_search_tool_bm25_20251119", "category": "server", "beta_header": null }, { "type": "advisor_20260301", "category": "server", "beta_header": "advisor-tool-2026-03-01" }, { "type": "mcp_toolset", "category": "mcp", "beta_header": "mcp-client-2025-11-20" }, { "type": "memory_20250818", "category": "client", "beta_header": null }, { "type": "bash_20250124", "category": "client", "beta_header": null }, { "type": "text_editor_20250728", "category": "client", "beta_header": null }, { "type": "computer_toolset_20260801", "category": "client", "beta_header": null }, { "type": "browser_toolset_20260801", "category": "client", "beta_header": null }, { "type": "computer_20251124", "category": "client", "beta_header": "computer-use-2025-11-24" } ], "endpoints": [ "POST /v1/messages", "POST /v1/messages/count_tokens", "POST /v1/messages/batches", "GET /v1/models/{model_id}", "Managed Agents (/v1/agents, /v1/sessions) — see managed-agents docs for per-model support" ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5, "batch_input": 2.5, "batch_output": 12.5, "batch_discount": 0.5, "long_context_over_200k": "standard pricing (no premium) for 1M-context models", "inference_geo_us_multiplier": 1.1, "priority_tier": "not supported", "cache_read_multiplier": 0.1, "fast_mode": { "input": 10, "output": 50, "note": "speed: fast, research preview, Claude API only; caching/data-residency multipliers stack; not on Batch" }, "tool_use_system_prompt_tokens": { "auto_or_none": 286, "any_or_tool": 406 } }, "rate_limits": { "class": "opus-5 (own bucket)", "ref": "generated/fragments/rate-limits/anthropic-rate-limits.json", "doc": "https://platform.claude.com/docs/en/api/rate-limits" }, "beta_headers": [ "advisor-tool-2026-03-01", "compact-2026-01-12", "compact-2026-09-04", "computer-use-2025-11-24", "fast-mode-2026-02-01", "mcp-client-2025-11-20", "mid-conversation-output-config-2026-07-01", "mid-conversation-tool-changes-2026-07-01", "output-300k-2026-03-24", "task-budgets-2026-03-13" ], "restrictions": { "data_retention": null, "access": null, "tool_choice": null, "thinking_disable": "only at effort high or below (400 at xhigh/max)" }, "availability": { "account": "available", "platforms": [ "Claude API", "Amazon Bedrock", "Google Cloud (Vertex AI)", "Microsoft Foundry", "Claude Platform on AWS" ], "cloud_ids": { "bedrock": [ "anthropic.claude-opus-5" ], "vertex": "claude-opus-5", "foundry": "claude-opus-5", "claude_platform_on_aws": "claude-opus-5" }, "regions": "Claude API is global by default; inference_geo us/global on 4.6+; Bedrock/Vertex regional endpoints +10%" }, "deprecation": { "state": "Active (latest)", "deprecated_on": null, "retirement": "not sooner than 2027-07-24", "replacement": null }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 200, "request_note": "GET /v1/models/claude-opus-5 -> 200", "messages_probe": { "http_status": 200, "usage": { "input_tokens": 13, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0, "cache_creation": { "ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0 }, "output_tokens": 4, "output_tokens_details": { "thinking_tokens": 0 }, "service_tier": "standard", "inference_geo": "global" }, "stop_reason": "end_turn" } }, "sources": [ { "url": "https://platform.claude.com/docs/en/models/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/models/opus-5/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/api/models/list", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/thinking", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/effort", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/prompt-caching", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/context-windows", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-opus-4-8", "display_name": "Claude Opus 4.8", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-opus-4-8" ], "family": "Opus", "generation": "4.8", "description": "Opus 4.x line; same tools/features as Opus 4.7", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "LEGACY" ], "lifecycle_docs": "Active (legacy)", "release_date": "2026-05-28", "created_at_live": "2026-05-28T00:00:00Z", "knowledge_cutoff": { "reliable": "Jan 2026", "training_data": "Jan 2026" }, "context_window": 1000000, "context_window_note": "1M default, no beta header, standard pricing", "max_output": 128000, "max_output_batch_beta": 300000, "live_max_input_tokens": 1000000, "live_max_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "thinking": "adaptive", "capabilities": { "text_input": true, "vision": true, "pdf_input": true, "high_resolution_vision_2576px": true, "tool_use": true, "parallel_tool_use": true, "tool_choice_any_or_tool": true, "strict_tool_use": true, "structured_outputs_json": true, "fine_grained_tool_streaming": true, "thinking_extended_manual_budget": false, "thinking_adaptive": true, "thinking_always_on": false, "thinking_on_by_default": false, "thinking_can_be_disabled": true, "interleaved_thinking": true, "thinking_display_omitted_default": true, "progress_updates_between_tool_calls": false, "effort_parameter": true, "effort_levels": [ "low", "medium", "high", "xhigh", "max" ], "effort_default": "high", "per_message_effort_beta": false, "fast_mode_speed_fast": true, "prompt_caching": true, "prompt_caching_1h_ttl": true, "automatic_caching_top_level_cache_control": true, "min_cacheable_tokens": 1024, "batch_api": true, "batch_extended_output_300k_beta": true, "citations": true, "files_api": true, "web_search": true, "web_search_dynamic_filtering": true, "web_fetch": true, "web_fetch_dynamic_filtering": true, "code_execution": true, "code_execution_docs": true, "programmatic_tool_calling": true, "computer_use": true, "computer_use_toolset_ga": true, "browser_use": true, "memory_tool": true, "text_editor_tool": true, "bash_tool": true, "tool_search": true, "advisor_tool": true, "mcp_connector": true, "agent_skills": true, "context_editing_clear_tool_uses": true, "context_editing_clear_thinking": true, "compaction_server_side": true, "compact_on_demand_beta": true, "context_1m_default_no_beta": true, "inference_geo_data_residency": true, "mid_conversation_system_messages": true, "mid_conversation_tool_changes_beta": true, "task_budgets_beta": true, "sampling_params_temperature_top_p_top_k": "rejected with 400 when non-default", "assistant_prefill": "unknown", "priority_tier": true, "zero_data_retention_eligible": true, "tokenizer": "new tokenizer (Claude 4.7+, ~30% more tokens)", "multilingual": true, "latency_class": null, "output_modalities": [ "text" ] }, "live_capabilities": { "batch": { "supported": true }, "citations": { "supported": true }, "code_execution": { "supported": true }, "context_management": { "supported": true, "clear_tool_uses_20250919": { "supported": true }, "clear_thinking_20251015": { "supported": true }, "compact_20260112": { "supported": true } }, "effort": { "supported": true, "low": { "supported": true }, "medium": { "supported": true }, "high": { "supported": true }, "xhigh": { "supported": true }, "max": { "supported": true } }, "image_input": { "supported": true }, "pdf_input": { "supported": true }, "structured_outputs": { "supported": true }, "thinking": { "supported": true, "types": { "enabled": { "supported": false }, "adaptive": { "supported": true } } } }, "tools": [ { "type": "web_search_20260318", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20260209", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20250305", "category": "server", "beta_header": null }, { "type": "web_fetch_20260318", "category": "server", "beta_header": null }, { "type": "web_fetch_20260309", "category": "server", "beta_header": null }, { "type": "web_fetch_20260209", "category": "server", "beta_header": null }, { "type": "web_fetch_20250910", "category": "server", "beta_header": null }, { "type": "code_execution_20260521", "category": "server", "beta_header": null }, { "type": "code_execution_20260120", "category": "server", "beta_header": null }, { "type": "code_execution_20250825", "category": "server", "beta_header": null }, { "type": "tool_search_tool_regex_20251119", "category": "server", "beta_header": null }, { "type": "tool_search_tool_bm25_20251119", "category": "server", "beta_header": null }, { "type": "advisor_20260301", "category": "server", "beta_header": "advisor-tool-2026-03-01" }, { "type": "mcp_toolset", "category": "mcp", "beta_header": "mcp-client-2025-11-20" }, { "type": "memory_20250818", "category": "client", "beta_header": null }, { "type": "bash_20250124", "category": "client", "beta_header": null }, { "type": "text_editor_20250728", "category": "client", "beta_header": null }, { "type": "computer_toolset_20260801", "category": "client", "beta_header": null }, { "type": "browser_toolset_20260801", "category": "client", "beta_header": null }, { "type": "computer_20251124", "category": "client", "beta_header": "computer-use-2025-11-24" } ], "endpoints": [ "POST /v1/messages", "POST /v1/messages/count_tokens", "POST /v1/messages/batches", "GET /v1/models/{model_id}", "Managed Agents (/v1/agents, /v1/sessions) — see managed-agents docs for per-model support" ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5, "batch_input": 2.5, "batch_output": 12.5, "batch_discount": 0.5, "long_context_over_200k": "standard pricing (no premium) for 1M-context models", "inference_geo_us_multiplier": 1.1, "priority_tier": "same token prices; capacity commitment, no longer sold", "cache_read_multiplier": 0.1, "fast_mode": { "input": 10, "output": 50, "note": "speed: fast, research preview, Claude API only; caching/data-residency multipliers stack; not on Batch" }, "tool_use_system_prompt_tokens": { "auto_or_none": 290, "any_or_tool": 410 } }, "rate_limits": { "class": "opus-4.x (shared 4.8/4.7/4.6/4.5)", "ref": "generated/fragments/rate-limits/anthropic-rate-limits.json", "doc": "https://platform.claude.com/docs/en/api/rate-limits" }, "beta_headers": [ "advisor-tool-2026-03-01", "compact-2026-01-12", "compact-2026-09-04", "computer-use-2025-11-24", "fast-mode-2026-02-01", "mcp-client-2025-11-20", "mid-conversation-tool-changes-2026-07-01", "output-300k-2026-03-24", "task-budgets-2026-03-13" ], "restrictions": { "data_retention": null, "access": null, "tool_choice": null, "thinking_disable": null }, "availability": { "account": "available", "platforms": [ "Claude API", "Amazon Bedrock", "Google Cloud (Vertex AI)", "Microsoft Foundry", "Claude Platform on AWS" ], "cloud_ids": { "bedrock": [ "anthropic.claude-opus-4-8" ], "vertex": "claude-opus-4-8", "foundry": "claude-opus-4-8", "claude_platform_on_aws": "claude-opus-4-8" }, "regions": "Claude API is global by default; inference_geo us/global on 4.6+; Bedrock/Vertex regional endpoints +10%" }, "deprecation": { "state": "Active (legacy)", "deprecated_on": null, "retirement": "not sooner than 2027-05-28", "replacement": null }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 200, "request_note": "GET /v1/models/claude-opus-4-8 -> 200", "messages_probe": { "http_status": 200, "usage": { "input_tokens": 13, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0, "cache_creation": { "ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0 }, "output_tokens": 4, "output_tokens_details": { "thinking_tokens": 0 }, "service_tier": "standard", "inference_geo": "global" }, "stop_reason": "end_turn" } }, "sources": [ { "url": "https://platform.claude.com/docs/en/models/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/models/opus-4-8/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/api/models/list", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/thinking", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/effort", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/prompt-caching", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/context-windows", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-opus-4-7", "display_name": "Claude Opus 4.7", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-opus-4-7" ], "family": "Opus", "generation": "4.7", "description": "Introduced the new tokenizer (+~30% tokens), xhigh effort, high-res vision", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "LEGACY" ], "lifecycle_docs": "Active (legacy)", "release_date": "2026-04-16", "created_at_live": "2026-04-14T00:00:00Z", "knowledge_cutoff": { "reliable": "Jan 2026", "training_data": "Jan 2026" }, "context_window": 1000000, "context_window_note": "1M default, no beta header, standard pricing", "max_output": 128000, "max_output_batch_beta": 300000, "live_max_input_tokens": 1000000, "live_max_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "thinking": "adaptive", "capabilities": { "text_input": true, "vision": true, "pdf_input": true, "high_resolution_vision_2576px": true, "tool_use": true, "parallel_tool_use": true, "tool_choice_any_or_tool": true, "strict_tool_use": true, "structured_outputs_json": true, "fine_grained_tool_streaming": true, "thinking_extended_manual_budget": false, "thinking_adaptive": true, "thinking_always_on": false, "thinking_on_by_default": false, "thinking_can_be_disabled": true, "interleaved_thinking": true, "thinking_display_omitted_default": true, "progress_updates_between_tool_calls": false, "effort_parameter": true, "effort_levels": [ "low", "medium", "high", "xhigh", "max" ], "effort_default": "high", "per_message_effort_beta": false, "fast_mode_speed_fast": false, "prompt_caching": true, "prompt_caching_1h_ttl": true, "automatic_caching_top_level_cache_control": true, "min_cacheable_tokens": 2048, "batch_api": true, "batch_extended_output_300k_beta": true, "citations": true, "files_api": true, "web_search": true, "web_search_dynamic_filtering": true, "web_fetch": true, "web_fetch_dynamic_filtering": true, "code_execution": true, "code_execution_docs": true, "programmatic_tool_calling": true, "computer_use": true, "computer_use_toolset_ga": false, "browser_use": false, "memory_tool": true, "text_editor_tool": true, "bash_tool": true, "tool_search": true, "advisor_tool": true, "mcp_connector": true, "agent_skills": true, "context_editing_clear_tool_uses": true, "context_editing_clear_thinking": true, "compaction_server_side": true, "compact_on_demand_beta": true, "context_1m_default_no_beta": true, "inference_geo_data_residency": true, "mid_conversation_system_messages": false, "mid_conversation_tool_changes_beta": false, "task_budgets_beta": true, "sampling_params_temperature_top_p_top_k": "rejected with 400 when non-default", "assistant_prefill": "unknown", "priority_tier": true, "zero_data_retention_eligible": true, "tokenizer": "new tokenizer (Claude 4.7+, ~30% more tokens)", "multilingual": true, "latency_class": null, "output_modalities": [ "text" ] }, "live_capabilities": { "batch": { "supported": true }, "citations": { "supported": true }, "code_execution": { "supported": true }, "context_management": { "supported": true, "clear_tool_uses_20250919": { "supported": true }, "clear_thinking_20251015": { "supported": true }, "compact_20260112": { "supported": true } }, "effort": { "supported": true, "low": { "supported": true }, "medium": { "supported": true }, "high": { "supported": true }, "xhigh": { "supported": true }, "max": { "supported": true } }, "image_input": { "supported": true }, "pdf_input": { "supported": true }, "structured_outputs": { "supported": true }, "thinking": { "supported": true, "types": { "enabled": { "supported": false }, "adaptive": { "supported": true } } } }, "tools": [ { "type": "web_search_20260318", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20260209", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20250305", "category": "server", "beta_header": null }, { "type": "web_fetch_20260318", "category": "server", "beta_header": null }, { "type": "web_fetch_20260309", "category": "server", "beta_header": null }, { "type": "web_fetch_20260209", "category": "server", "beta_header": null }, { "type": "web_fetch_20250910", "category": "server", "beta_header": null }, { "type": "code_execution_20260521", "category": "server", "beta_header": null }, { "type": "code_execution_20260120", "category": "server", "beta_header": null }, { "type": "code_execution_20250825", "category": "server", "beta_header": null }, { "type": "tool_search_tool_regex_20251119", "category": "server", "beta_header": null }, { "type": "tool_search_tool_bm25_20251119", "category": "server", "beta_header": null }, { "type": "advisor_20260301", "category": "server", "beta_header": "advisor-tool-2026-03-01" }, { "type": "mcp_toolset", "category": "mcp", "beta_header": "mcp-client-2025-11-20" }, { "type": "memory_20250818", "category": "client", "beta_header": null }, { "type": "bash_20250124", "category": "client", "beta_header": null }, { "type": "text_editor_20250728", "category": "client", "beta_header": null }, { "type": "computer_20251124", "category": "client", "beta_header": "computer-use-2025-11-24" } ], "endpoints": [ "POST /v1/messages", "POST /v1/messages/count_tokens", "POST /v1/messages/batches", "GET /v1/models/{model_id}", "Managed Agents (/v1/agents, /v1/sessions) — see managed-agents docs for per-model support" ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5, "batch_input": 2.5, "batch_output": 12.5, "batch_discount": 0.5, "long_context_over_200k": "standard pricing (no premium) for 1M-context models", "inference_geo_us_multiplier": 1.1, "priority_tier": "same token prices; capacity commitment, no longer sold", "cache_read_multiplier": 0.1, "tool_use_system_prompt_tokens": { "auto_or_none": 675, "any_or_tool": 804 } }, "rate_limits": { "class": "opus-4.x (shared 4.8/4.7/4.6/4.5)", "ref": "generated/fragments/rate-limits/anthropic-rate-limits.json", "doc": "https://platform.claude.com/docs/en/api/rate-limits" }, "beta_headers": [ "advisor-tool-2026-03-01", "compact-2026-01-12", "compact-2026-09-04", "computer-use-2025-11-24", "mcp-client-2025-11-20", "output-300k-2026-03-24", "task-budgets-2026-03-13" ], "restrictions": { "data_retention": null, "access": null, "tool_choice": null, "thinking_disable": null }, "availability": { "account": "available", "platforms": [ "Claude API", "Amazon Bedrock", "Google Cloud (Vertex AI)", "Microsoft Foundry", "Claude Platform on AWS" ], "cloud_ids": { "bedrock": [ "anthropic.claude-opus-4-7" ], "vertex": "claude-opus-4-7", "foundry": "claude-opus-4-7", "claude_platform_on_aws": "claude-opus-4-7" }, "regions": "Claude API is global by default; inference_geo us/global on 4.6+; Bedrock/Vertex regional endpoints +10%" }, "deprecation": { "state": "Active (legacy)", "deprecated_on": null, "retirement": "not sooner than 2027-04-16", "replacement": null }, "discrepancies_live_vs_docs": [ "live created_at 2026-04-14 != documented release 2026-04-16" ], "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 200, "request_note": "GET /v1/models/claude-opus-4-7 -> 200" }, "sources": [ { "url": "https://platform.claude.com/docs/en/models/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/models/opus-4-7/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/api/models/list", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/thinking", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/effort", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/prompt-caching", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/context-windows", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-opus-4-6", "display_name": "Claude Opus 4.6", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-opus-4-6" ], "family": "Opus", "generation": "4.6", "description": "First dateless ID; last Bedrock ID with -v1 suffix", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "LEGACY" ], "lifecycle_docs": "Active (legacy)", "release_date": "2026-02-05", "created_at_live": "2026-02-04T00:00:00Z", "knowledge_cutoff": { "reliable": "May 2025", "training_data": "Aug 2025" }, "context_window": 1000000, "context_window_note": "1M default, no beta header, standard pricing", "max_output": 128000, "max_output_batch_beta": 300000, "live_max_input_tokens": 1000000, "live_max_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "thinking": "adaptive (manual extended deprecated)", "capabilities": { "text_input": true, "vision": true, "pdf_input": true, "high_resolution_vision_2576px": false, "tool_use": true, "parallel_tool_use": true, "tool_choice_any_or_tool": true, "strict_tool_use": true, "structured_outputs_json": true, "fine_grained_tool_streaming": true, "thinking_extended_manual_budget": true, "thinking_adaptive": true, "thinking_always_on": false, "thinking_on_by_default": false, "thinking_can_be_disabled": true, "interleaved_thinking": true, "thinking_display_omitted_default": false, "progress_updates_between_tool_calls": false, "effort_parameter": true, "effort_levels": [ "low", "medium", "high", "max" ], "effort_default": "high", "per_message_effort_beta": false, "fast_mode_speed_fast": false, "prompt_caching": true, "prompt_caching_1h_ttl": true, "automatic_caching_top_level_cache_control": true, "min_cacheable_tokens": 4096, "batch_api": true, "batch_extended_output_300k_beta": true, "citations": true, "files_api": true, "web_search": true, "web_search_dynamic_filtering": true, "web_fetch": true, "web_fetch_dynamic_filtering": true, "code_execution": true, "code_execution_docs": true, "programmatic_tool_calling": true, "computer_use": true, "computer_use_toolset_ga": false, "browser_use": false, "memory_tool": true, "text_editor_tool": true, "bash_tool": true, "tool_search": true, "advisor_tool": true, "mcp_connector": true, "agent_skills": true, "context_editing_clear_tool_uses": true, "context_editing_clear_thinking": true, "compaction_server_side": true, "compact_on_demand_beta": true, "context_1m_default_no_beta": true, "inference_geo_data_residency": true, "mid_conversation_system_messages": false, "mid_conversation_tool_changes_beta": false, "task_budgets_beta": false, "sampling_params_temperature_top_p_top_k": "accepted (incompatible with thinking on)", "assistant_prefill": false, "priority_tier": true, "zero_data_retention_eligible": true, "tokenizer": "previous tokenizer", "multilingual": true, "latency_class": null, "output_modalities": [ "text" ] }, "live_capabilities": { "batch": { "supported": true }, "citations": { "supported": true }, "code_execution": { "supported": true }, "context_management": { "supported": true, "clear_tool_uses_20250919": { "supported": true }, "clear_thinking_20251015": { "supported": true }, "compact_20260112": { "supported": true } }, "effort": { "supported": true, "low": { "supported": true }, "medium": { "supported": true }, "high": { "supported": true }, "xhigh": { "supported": false }, "max": { "supported": true } }, "image_input": { "supported": true }, "pdf_input": { "supported": true }, "structured_outputs": { "supported": true }, "thinking": { "supported": true, "types": { "enabled": { "supported": true }, "adaptive": { "supported": true } } } }, "tools": [ { "type": "web_search_20260318", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20260209", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20250305", "category": "server", "beta_header": null }, { "type": "web_fetch_20260318", "category": "server", "beta_header": null }, { "type": "web_fetch_20260309", "category": "server", "beta_header": null }, { "type": "web_fetch_20260209", "category": "server", "beta_header": null }, { "type": "web_fetch_20250910", "category": "server", "beta_header": null }, { "type": "code_execution_20260521", "category": "server", "beta_header": null }, { "type": "code_execution_20260120", "category": "server", "beta_header": null }, { "type": "code_execution_20250825", "category": "server", "beta_header": null }, { "type": "tool_search_tool_regex_20251119", "category": "server", "beta_header": null }, { "type": "tool_search_tool_bm25_20251119", "category": "server", "beta_header": null }, { "type": "advisor_20260301", "category": "server", "beta_header": "advisor-tool-2026-03-01" }, { "type": "mcp_toolset", "category": "mcp", "beta_header": "mcp-client-2025-11-20" }, { "type": "memory_20250818", "category": "client", "beta_header": null }, { "type": "bash_20250124", "category": "client", "beta_header": null }, { "type": "text_editor_20250728", "category": "client", "beta_header": null }, { "type": "computer_20251124", "category": "client", "beta_header": "computer-use-2025-11-24" } ], "endpoints": [ "POST /v1/messages", "POST /v1/messages/count_tokens", "POST /v1/messages/batches", "GET /v1/models/{model_id}", "Managed Agents (/v1/agents, /v1/sessions) — see managed-agents docs for per-model support" ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5, "batch_input": 2.5, "batch_output": 12.5, "batch_discount": 0.5, "long_context_over_200k": "standard pricing (no premium) for 1M-context models", "inference_geo_us_multiplier": 1.1, "priority_tier": "same token prices; capacity commitment, no longer sold", "cache_read_multiplier": 0.1, "tool_use_system_prompt_tokens": { "auto_or_none": 497, "any_or_tool": 589 } }, "rate_limits": { "class": "opus-4.x (shared 4.8/4.7/4.6/4.5)", "ref": "generated/fragments/rate-limits/anthropic-rate-limits.json", "doc": "https://platform.claude.com/docs/en/api/rate-limits" }, "beta_headers": [ "advisor-tool-2026-03-01", "compact-2026-01-12", "compact-2026-09-04", "computer-use-2025-11-24", "mcp-client-2025-11-20", "output-300k-2026-03-24" ], "restrictions": { "data_retention": null, "access": null, "tool_choice": null, "thinking_disable": null }, "availability": { "account": "available", "platforms": [ "Claude API", "Amazon Bedrock", "Google Cloud (Vertex AI)", "Microsoft Foundry", "Claude Platform on AWS" ], "cloud_ids": { "bedrock": [ "anthropic.claude-opus-4-6-v1" ], "vertex": "claude-opus-4-6", "foundry": "claude-opus-4-6", "claude_platform_on_aws": "claude-opus-4-6" }, "regions": "Claude API is global by default; inference_geo us/global on 4.6+; Bedrock/Vertex regional endpoints +10%" }, "deprecation": { "state": "Active (legacy)", "deprecated_on": null, "retirement": "not sooner than 2027-02-05", "replacement": null }, "discrepancies_live_vs_docs": [ "live created_at 2026-02-04 != documented release 2026-02-05" ], "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 200, "request_note": "GET /v1/models/claude-opus-4-6 -> 200" }, "sources": [ { "url": "https://platform.claude.com/docs/en/models/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/models/opus-4-6/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/api/models/list", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/thinking", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/effort", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/prompt-caching", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/context-windows", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-opus-4-5-20251101", "display_name": "Claude Opus 4.5", "kind": "snapshot", "aliases": [ "claude-opus-4-5" ], "snapshots": [ "claude-opus-4-5-20251101" ], "family": "Opus", "generation": "4.5", "description": "Last dated Opus snapshot", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "LEGACY" ], "lifecycle_docs": "Active (legacy)", "release_date": "2025-11-24", "created_at_live": "2025-11-24T00:00:00Z", "knowledge_cutoff": { "reliable": "May 2025", "training_data": "Aug 2025" }, "context_window": 200000, "context_window_note": "200k", "max_output": 64000, "max_output_batch_beta": null, "live_max_input_tokens": 200000, "live_max_tokens": 64000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "thinking": "extended (manual)", "capabilities": { "text_input": true, "vision": true, "pdf_input": true, "high_resolution_vision_2576px": false, "tool_use": true, "parallel_tool_use": true, "tool_choice_any_or_tool": true, "strict_tool_use": true, "structured_outputs_json": true, "fine_grained_tool_streaming": true, "thinking_extended_manual_budget": true, "thinking_adaptive": false, "thinking_always_on": false, "thinking_on_by_default": false, "thinking_can_be_disabled": true, "interleaved_thinking": "beta header interleaved-thinking-2025-05-14 with manual thinking", "thinking_display_omitted_default": false, "progress_updates_between_tool_calls": false, "effort_parameter": true, "effort_levels": [ "low", "medium", "high" ], "effort_default": "high", "per_message_effort_beta": false, "fast_mode_speed_fast": false, "prompt_caching": true, "prompt_caching_1h_ttl": true, "automatic_caching_top_level_cache_control": true, "min_cacheable_tokens": 4096, "batch_api": true, "batch_extended_output_300k_beta": false, "citations": true, "files_api": true, "web_search": true, "web_search_dynamic_filtering": false, "web_fetch": true, "web_fetch_dynamic_filtering": false, "code_execution": true, "code_execution_docs": true, "programmatic_tool_calling": true, "computer_use": true, "computer_use_toolset_ga": false, "browser_use": false, "memory_tool": true, "text_editor_tool": true, "bash_tool": true, "tool_search": true, "advisor_tool": true, "mcp_connector": true, "agent_skills": true, "context_editing_clear_tool_uses": true, "context_editing_clear_thinking": true, "compaction_server_side": false, "compact_on_demand_beta": false, "context_1m_default_no_beta": false, "inference_geo_data_residency": false, "mid_conversation_system_messages": false, "mid_conversation_tool_changes_beta": false, "task_budgets_beta": false, "sampling_params_temperature_top_p_top_k": "accepted (incompatible with thinking on)", "assistant_prefill": "unknown", "priority_tier": true, "zero_data_retention_eligible": true, "tokenizer": "previous tokenizer", "multilingual": true, "latency_class": null, "output_modalities": [ "text" ] }, "live_capabilities": { "batch": { "supported": true }, "citations": { "supported": true }, "code_execution": { "supported": true }, "context_management": { "supported": true, "clear_tool_uses_20250919": { "supported": true }, "clear_thinking_20251015": { "supported": true }, "compact_20260112": { "supported": false } }, "effort": { "supported": true, "low": { "supported": true }, "medium": { "supported": true }, "high": { "supported": true }, "xhigh": { "supported": false }, "max": { "supported": false } }, "image_input": { "supported": true }, "pdf_input": { "supported": true }, "structured_outputs": { "supported": true }, "thinking": { "supported": true, "types": { "enabled": { "supported": true }, "adaptive": { "supported": false } } } }, "tools": [ { "type": "web_search_20250305", "category": "server", "beta_header": null }, { "type": "web_fetch_20250910", "category": "server", "beta_header": null }, { "type": "code_execution_20260521", "category": "server", "beta_header": null }, { "type": "code_execution_20260120", "category": "server", "beta_header": null }, { "type": "code_execution_20250825", "category": "server", "beta_header": null }, { "type": "tool_search_tool_regex_20251119", "category": "server", "beta_header": null }, { "type": "tool_search_tool_bm25_20251119", "category": "server", "beta_header": null }, { "type": "advisor_20260301", "category": "server", "beta_header": "advisor-tool-2026-03-01" }, { "type": "mcp_toolset", "category": "mcp", "beta_header": "mcp-client-2025-11-20" }, { "type": "memory_20250818", "category": "client", "beta_header": null }, { "type": "bash_20250124", "category": "client", "beta_header": null }, { "type": "text_editor_20250728", "category": "client", "beta_header": null }, { "type": "computer_20251124", "category": "client", "beta_header": "computer-use-2025-11-24" } ], "endpoints": [ "POST /v1/messages", "POST /v1/messages/count_tokens", "POST /v1/messages/batches", "GET /v1/models/{model_id}", "Managed Agents (/v1/agents, /v1/sessions) — see managed-agents docs for per-model support" ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5, "batch_input": 2.5, "batch_output": 12.5, "batch_discount": 0.5, "long_context_over_200k": "n/a (200k context)", "inference_geo_us_multiplier": null, "priority_tier": "same token prices; capacity commitment, no longer sold", "cache_read_multiplier": 0.1, "tool_use_system_prompt_tokens": { "auto_or_none": 496, "any_or_tool": 588 } }, "rate_limits": { "class": "opus-4.x (shared 4.8/4.7/4.6/4.5)", "ref": "generated/fragments/rate-limits/anthropic-rate-limits.json", "doc": "https://platform.claude.com/docs/en/api/rate-limits" }, "beta_headers": [ "advisor-tool-2026-03-01", "computer-use-2025-11-24", "interleaved-thinking-2025-05-14", "mcp-client-2025-11-20" ], "restrictions": { "data_retention": null, "access": null, "tool_choice": null, "thinking_disable": null }, "availability": { "account": "available", "platforms": [ "Claude API", "Amazon Bedrock", "Google Cloud (Vertex AI)", "Microsoft Foundry", "Claude Platform on AWS" ], "cloud_ids": { "bedrock": [ "anthropic.claude-opus-4-5-20251101-v1:0" ], "vertex": "claude-opus-4-5@20251101", "foundry": "claude-opus-4-5", "claude_platform_on_aws": "claude-opus-4-5" }, "regions": "Claude API is global by default; inference_geo us/global on 4.6+; Bedrock/Vertex regional endpoints +10%" }, "deprecation": { "state": "Active (legacy)", "deprecated_on": null, "retirement": "not sooner than 2026-11-24", "replacement": null }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 200, "request_note": "GET /v1/models/claude-opus-4-5-20251101 -> 200" }, "sources": [ { "url": "https://platform.claude.com/docs/en/models/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/models/opus-4-5/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/api/models/list", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/thinking", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/effort", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/prompt-caching", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/context-windows", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-opus-4-5", "display_name": "Claude Opus 4.5 (alias)", "kind": "alias", "resolves_to": "claude-opus-4-5-20251101", "aliases": [], "snapshots": [ "claude-opus-4-5-20251101" ], "family": "Opus", "generation": "4.5", "description": "Convenience alias; GET /v1/models/claude-opus-4-5 resolves to claude-opus-4-5-20251101. Aliases exist only for pre-4.6 models.", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "release_date": "2025-11-24", "context_window": 200000, "max_output": 64000, "pricing": "same as claude-opus-4-5-20251101", "endpoints": [ "POST /v1/messages", "GET /v1/models/{model_id}" ], "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 200, "request_note": "GET /v1/models/claude-opus-4-5 -> id claude-opus-4-5-20251101" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/models/model-ids-and-versions", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/models/opus-4-5/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-sonnet-5", "display_name": "Claude Sonnet 5", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-sonnet-5" ], "family": "Sonnet", "generation": "5", "description": "The best combination of speed and intelligence", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "lifecycle_docs": "Active (latest)", "release_date": "2026-06-30", "created_at_live": "2026-06-29T00:00:00Z", "knowledge_cutoff": { "reliable": "Jan 2026", "training_data": "Jan 2026" }, "context_window": 1000000, "context_window_note": "1M default, no beta header, standard pricing", "max_output": 128000, "max_output_batch_beta": 300000, "live_max_input_tokens": 1000000, "live_max_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "thinking": "adaptive (on by default)", "capabilities": { "text_input": true, "vision": true, "pdf_input": true, "high_resolution_vision_2576px": true, "tool_use": true, "parallel_tool_use": true, "tool_choice_any_or_tool": true, "strict_tool_use": true, "structured_outputs_json": true, "fine_grained_tool_streaming": true, "thinking_extended_manual_budget": false, "thinking_adaptive": true, "thinking_always_on": false, "thinking_on_by_default": true, "thinking_can_be_disabled": true, "interleaved_thinking": true, "thinking_display_omitted_default": true, "progress_updates_between_tool_calls": false, "effort_parameter": true, "effort_levels": [ "low", "medium", "high", "xhigh", "max" ], "effort_default": "high", "per_message_effort_beta": false, "fast_mode_speed_fast": false, "prompt_caching": true, "prompt_caching_1h_ttl": true, "automatic_caching_top_level_cache_control": true, "min_cacheable_tokens": 1024, "batch_api": true, "batch_extended_output_300k_beta": true, "citations": true, "files_api": true, "web_search": true, "web_search_dynamic_filtering": true, "web_fetch": true, "web_fetch_dynamic_filtering": true, "code_execution": true, "code_execution_docs": true, "programmatic_tool_calling": true, "computer_use": true, "computer_use_toolset_ga": true, "browser_use": true, "memory_tool": true, "text_editor_tool": true, "bash_tool": true, "tool_search": true, "advisor_tool": true, "mcp_connector": true, "agent_skills": true, "context_editing_clear_tool_uses": true, "context_editing_clear_thinking": true, "compaction_server_side": true, "compact_on_demand_beta": true, "context_1m_default_no_beta": true, "inference_geo_data_residency": true, "mid_conversation_system_messages": false, "mid_conversation_tool_changes_beta": false, "task_budgets_beta": false, "sampling_params_temperature_top_p_top_k": "rejected with 400 when non-default", "assistant_prefill": false, "priority_tier": false, "zero_data_retention_eligible": true, "tokenizer": "new tokenizer (Claude 4.7+, ~30% more tokens)", "multilingual": true, "latency_class": "Fast", "output_modalities": [ "text" ] }, "live_capabilities": { "batch": { "supported": true }, "citations": { "supported": true }, "code_execution": { "supported": true }, "context_management": { "supported": true, "clear_tool_uses_20250919": { "supported": true }, "clear_thinking_20251015": { "supported": true }, "compact_20260112": { "supported": true } }, "effort": { "supported": true, "low": { "supported": true }, "medium": { "supported": true }, "high": { "supported": true }, "xhigh": { "supported": true }, "max": { "supported": true } }, "image_input": { "supported": true }, "pdf_input": { "supported": true }, "structured_outputs": { "supported": true }, "thinking": { "supported": true, "types": { "enabled": { "supported": false }, "adaptive": { "supported": true } } } }, "tools": [ { "type": "web_search_20260318", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20260209", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20250305", "category": "server", "beta_header": null }, { "type": "web_fetch_20260318", "category": "server", "beta_header": null }, { "type": "web_fetch_20260309", "category": "server", "beta_header": null }, { "type": "web_fetch_20260209", "category": "server", "beta_header": null }, { "type": "web_fetch_20250910", "category": "server", "beta_header": null }, { "type": "code_execution_20260521", "category": "server", "beta_header": null }, { "type": "code_execution_20260120", "category": "server", "beta_header": null }, { "type": "code_execution_20250825", "category": "server", "beta_header": null }, { "type": "tool_search_tool_regex_20251119", "category": "server", "beta_header": null }, { "type": "tool_search_tool_bm25_20251119", "category": "server", "beta_header": null }, { "type": "advisor_20260301", "category": "server", "beta_header": "advisor-tool-2026-03-01" }, { "type": "mcp_toolset", "category": "mcp", "beta_header": "mcp-client-2025-11-20" }, { "type": "memory_20250818", "category": "client", "beta_header": null }, { "type": "bash_20250124", "category": "client", "beta_header": null }, { "type": "text_editor_20250728", "category": "client", "beta_header": null }, { "type": "computer_toolset_20260801", "category": "client", "beta_header": null }, { "type": "browser_toolset_20260801", "category": "client", "beta_header": null }, { "type": "computer_20251124", "category": "client", "beta_header": "computer-use-2025-11-24" } ], "endpoints": [ "POST /v1/messages", "POST /v1/messages/count_tokens", "POST /v1/messages/batches", "GET /v1/models/{model_id}", "Managed Agents (/v1/agents, /v1/sessions) — see managed-agents docs for per-model support" ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "input": 2, "output": 10, "cache_write_5m": 2.5, "cache_write_1h": 4, "cache_read": 0.2, "batch_input": 1.0, "batch_output": 5.0, "batch_discount": 0.5, "long_context_over_200k": "standard pricing (no premium) for 1M-context models", "inference_geo_us_multiplier": 1.1, "priority_tier": "not supported", "cache_read_multiplier": 0.1, "tool_use_system_prompt_tokens": { "auto_or_none": 354, "any_or_tool": 474 } }, "rate_limits": { "class": "sonnet-5 (own bucket)", "ref": "generated/fragments/rate-limits/anthropic-rate-limits.json", "doc": "https://platform.claude.com/docs/en/api/rate-limits" }, "beta_headers": [ "advisor-tool-2026-03-01", "compact-2026-01-12", "compact-2026-09-04", "computer-use-2025-11-24", "mcp-client-2025-11-20", "output-300k-2026-03-24" ], "restrictions": { "data_retention": null, "access": null, "tool_choice": null, "thinking_disable": null }, "availability": { "account": "available", "platforms": [ "Claude API", "Amazon Bedrock", "Google Cloud (Vertex AI)", "Microsoft Foundry", "Claude Platform on AWS" ], "cloud_ids": { "bedrock": [ "anthropic.claude-sonnet-5" ], "vertex": "claude-sonnet-5", "foundry": "claude-sonnet-5", "claude_platform_on_aws": "claude-sonnet-5" }, "regions": "Claude API is global by default; inference_geo us/global on 4.6+; Bedrock/Vertex regional endpoints +10%" }, "deprecation": { "state": "Active (latest)", "deprecated_on": null, "retirement": "not sooner than 2027-06-30", "replacement": null }, "discrepancies_live_vs_docs": [ "live created_at 2026-06-29 != documented release 2026-06-30" ], "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 200, "request_note": "GET /v1/models/claude-sonnet-5 -> 200", "messages_probe": { "http_status": 200, "usage": { "input_tokens": 13, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0, "cache_creation": { "ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0 }, "output_tokens": 4, "output_tokens_details": { "thinking_tokens": 0 }, "service_tier": "standard", "inference_geo": "global" }, "stop_reason": "end_turn" } }, "sources": [ { "url": "https://platform.claude.com/docs/en/models/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/models/sonnet-5/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/api/models/list", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/thinking", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/effort", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/prompt-caching", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/context-windows", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-sonnet-4-6", "display_name": "Claude Sonnet 4.6", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-sonnet-4-6" ], "family": "Sonnet", "generation": "4.6", "description": "First Sonnet with dateless ID", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "LEGACY" ], "lifecycle_docs": "Active (legacy)", "release_date": "2026-02-17", "created_at_live": "2026-02-17T00:00:00Z", "knowledge_cutoff": { "reliable": "Aug 2025", "training_data": "Jan 2026" }, "context_window": 1000000, "context_window_note": "1M default, no beta header, standard pricing", "max_output": 128000, "max_output_batch_beta": 300000, "live_max_input_tokens": 1000000, "live_max_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "thinking": "adaptive (manual extended deprecated)", "capabilities": { "text_input": true, "vision": true, "pdf_input": true, "high_resolution_vision_2576px": false, "tool_use": true, "parallel_tool_use": true, "tool_choice_any_or_tool": true, "strict_tool_use": true, "structured_outputs_json": true, "fine_grained_tool_streaming": true, "thinking_extended_manual_budget": true, "thinking_adaptive": true, "thinking_always_on": false, "thinking_on_by_default": false, "thinking_can_be_disabled": true, "interleaved_thinking": true, "thinking_display_omitted_default": false, "progress_updates_between_tool_calls": false, "effort_parameter": true, "effort_levels": [ "low", "medium", "high", "max" ], "effort_default": "high", "per_message_effort_beta": false, "fast_mode_speed_fast": false, "prompt_caching": true, "prompt_caching_1h_ttl": true, "automatic_caching_top_level_cache_control": true, "min_cacheable_tokens": 1024, "batch_api": true, "batch_extended_output_300k_beta": true, "citations": true, "files_api": true, "web_search": true, "web_search_dynamic_filtering": true, "web_fetch": true, "web_fetch_dynamic_filtering": true, "code_execution": true, "code_execution_docs": true, "programmatic_tool_calling": true, "computer_use": true, "computer_use_toolset_ga": false, "browser_use": false, "memory_tool": true, "text_editor_tool": true, "bash_tool": true, "tool_search": true, "advisor_tool": true, "mcp_connector": true, "agent_skills": true, "context_editing_clear_tool_uses": true, "context_editing_clear_thinking": true, "compaction_server_side": true, "compact_on_demand_beta": true, "context_1m_default_no_beta": true, "inference_geo_data_residency": true, "mid_conversation_system_messages": false, "mid_conversation_tool_changes_beta": false, "task_budgets_beta": false, "sampling_params_temperature_top_p_top_k": "accepted (incompatible with thinking on)", "assistant_prefill": "unknown", "priority_tier": true, "zero_data_retention_eligible": true, "tokenizer": "previous tokenizer", "multilingual": true, "latency_class": null, "output_modalities": [ "text" ] }, "live_capabilities": { "batch": { "supported": true }, "citations": { "supported": true }, "code_execution": { "supported": true }, "context_management": { "supported": true, "clear_tool_uses_20250919": { "supported": true }, "clear_thinking_20251015": { "supported": true }, "compact_20260112": { "supported": true } }, "effort": { "supported": true, "low": { "supported": true }, "medium": { "supported": true }, "high": { "supported": true }, "xhigh": { "supported": false }, "max": { "supported": true } }, "image_input": { "supported": true }, "pdf_input": { "supported": true }, "structured_outputs": { "supported": true }, "thinking": { "supported": true, "types": { "enabled": { "supported": true }, "adaptive": { "supported": true } } } }, "tools": [ { "type": "web_search_20260318", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20260209", "category": "server", "beta_header": null, "note": "dynamic filtering (code execution) on 4.6+" }, { "type": "web_search_20250305", "category": "server", "beta_header": null }, { "type": "web_fetch_20260318", "category": "server", "beta_header": null }, { "type": "web_fetch_20260309", "category": "server", "beta_header": null }, { "type": "web_fetch_20260209", "category": "server", "beta_header": null }, { "type": "web_fetch_20250910", "category": "server", "beta_header": null }, { "type": "code_execution_20260521", "category": "server", "beta_header": null }, { "type": "code_execution_20260120", "category": "server", "beta_header": null }, { "type": "code_execution_20250825", "category": "server", "beta_header": null }, { "type": "tool_search_tool_regex_20251119", "category": "server", "beta_header": null }, { "type": "tool_search_tool_bm25_20251119", "category": "server", "beta_header": null }, { "type": "advisor_20260301", "category": "server", "beta_header": "advisor-tool-2026-03-01" }, { "type": "mcp_toolset", "category": "mcp", "beta_header": "mcp-client-2025-11-20" }, { "type": "memory_20250818", "category": "client", "beta_header": null }, { "type": "bash_20250124", "category": "client", "beta_header": null }, { "type": "text_editor_20250728", "category": "client", "beta_header": null }, { "type": "computer_20251124", "category": "client", "beta_header": "computer-use-2025-11-24" } ], "endpoints": [ "POST /v1/messages", "POST /v1/messages/count_tokens", "POST /v1/messages/batches", "GET /v1/models/{model_id}", "Managed Agents (/v1/agents, /v1/sessions) — see managed-agents docs for per-model support" ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "input": 3, "output": 15, "cache_write_5m": 3.75, "cache_write_1h": 6, "cache_read": 0.3, "batch_input": 1.5, "batch_output": 7.5, "batch_discount": 0.5, "long_context_over_200k": "standard pricing (no premium) for 1M-context models", "inference_geo_us_multiplier": 1.1, "priority_tier": "same token prices; capacity commitment, no longer sold", "cache_read_multiplier": 0.1, "tool_use_system_prompt_tokens": { "auto_or_none": 497, "any_or_tool": 589 } }, "rate_limits": { "class": "sonnet-4.x (shared 4.6/4.5)", "ref": "generated/fragments/rate-limits/anthropic-rate-limits.json", "doc": "https://platform.claude.com/docs/en/api/rate-limits" }, "beta_headers": [ "advisor-tool-2026-03-01", "compact-2026-01-12", "compact-2026-09-04", "computer-use-2025-11-24", "mcp-client-2025-11-20", "output-300k-2026-03-24" ], "restrictions": { "data_retention": null, "access": null, "tool_choice": null, "thinking_disable": null }, "availability": { "account": "available", "platforms": [ "Claude API", "Amazon Bedrock", "Google Cloud (Vertex AI)", "Microsoft Foundry", "Claude Platform on AWS" ], "cloud_ids": { "bedrock": [ "anthropic.claude-sonnet-4-6" ], "vertex": "claude-sonnet-4-6", "foundry": "claude-sonnet-4-6", "claude_platform_on_aws": "claude-sonnet-4-6" }, "regions": "Claude API is global by default; inference_geo us/global on 4.6+; Bedrock/Vertex regional endpoints +10%" }, "deprecation": { "state": "Active (legacy)", "deprecated_on": null, "retirement": "not sooner than 2027-02-17", "replacement": null }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 200, "request_note": "GET /v1/models/claude-sonnet-4-6 -> 200", "messages_probe": { "http_status": 200, "usage": { "input_tokens": 11, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0, "cache_creation": { "ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0 }, "output_tokens": 5, "service_tier": "standard", "inference_geo": "global" }, "stop_reason": "end_turn" } }, "sources": [ { "url": "https://platform.claude.com/docs/en/models/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/models/sonnet-4-6/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/api/models/list", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/thinking", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/effort", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/prompt-caching", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/context-windows", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-sonnet-4-5-20250929", "display_name": "Claude Sonnet 4.5", "kind": "snapshot", "aliases": [ "claude-sonnet-4-5" ], "snapshots": [ "claude-sonnet-4-5-20250929" ], "family": "Sonnet", "generation": "4.5", "description": "1M context beta retired for this model on 2026-04-30", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "LEGACY" ], "lifecycle_docs": "Active (legacy)", "release_date": "2025-09-29", "created_at_live": "2025-09-29T00:00:00Z", "knowledge_cutoff": { "reliable": "Jan 2025", "training_data": "Jul 2025" }, "context_window": 200000, "context_window_note": "200k", "max_output": 64000, "max_output_batch_beta": null, "live_max_input_tokens": 1000000, "live_max_tokens": 64000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "thinking": "extended (manual)", "capabilities": { "text_input": true, "vision": true, "pdf_input": true, "high_resolution_vision_2576px": false, "tool_use": true, "parallel_tool_use": true, "tool_choice_any_or_tool": true, "strict_tool_use": true, "structured_outputs_json": true, "fine_grained_tool_streaming": true, "thinking_extended_manual_budget": true, "thinking_adaptive": false, "thinking_always_on": false, "thinking_on_by_default": false, "thinking_can_be_disabled": true, "interleaved_thinking": "beta header interleaved-thinking-2025-05-14 with manual thinking", "thinking_display_omitted_default": false, "progress_updates_between_tool_calls": false, "effort_parameter": false, "effort_levels": [], "effort_default": null, "per_message_effort_beta": false, "fast_mode_speed_fast": false, "prompt_caching": true, "prompt_caching_1h_ttl": true, "automatic_caching_top_level_cache_control": true, "min_cacheable_tokens": 1024, "batch_api": true, "batch_extended_output_300k_beta": false, "citations": true, "files_api": true, "web_search": true, "web_search_dynamic_filtering": false, "web_fetch": true, "web_fetch_dynamic_filtering": false, "code_execution": true, "code_execution_docs": true, "programmatic_tool_calling": true, "computer_use": true, "computer_use_toolset_ga": false, "browser_use": false, "memory_tool": true, "text_editor_tool": true, "bash_tool": true, "tool_search": true, "advisor_tool": true, "mcp_connector": true, "agent_skills": true, "context_editing_clear_tool_uses": true, "context_editing_clear_thinking": true, "compaction_server_side": false, "compact_on_demand_beta": false, "context_1m_default_no_beta": false, "inference_geo_data_residency": false, "mid_conversation_system_messages": false, "mid_conversation_tool_changes_beta": false, "task_budgets_beta": false, "sampling_params_temperature_top_p_top_k": "accepted (incompatible with thinking on)", "assistant_prefill": "unknown", "priority_tier": true, "zero_data_retention_eligible": true, "tokenizer": "previous tokenizer", "multilingual": true, "latency_class": null, "output_modalities": [ "text" ] }, "live_capabilities": { "batch": { "supported": true }, "citations": { "supported": true }, "code_execution": { "supported": true }, "context_management": { "supported": true, "clear_tool_uses_20250919": { "supported": true }, "clear_thinking_20251015": { "supported": true }, "compact_20260112": { "supported": false } }, "effort": { "supported": false, "low": { "supported": false }, "medium": { "supported": false }, "high": { "supported": false }, "xhigh": { "supported": false }, "max": { "supported": false } }, "image_input": { "supported": true }, "pdf_input": { "supported": true }, "structured_outputs": { "supported": true }, "thinking": { "supported": true, "types": { "enabled": { "supported": true }, "adaptive": { "supported": false } } } }, "tools": [ { "type": "web_search_20250305", "category": "server", "beta_header": null }, { "type": "web_fetch_20250910", "category": "server", "beta_header": null }, { "type": "code_execution_20260521", "category": "server", "beta_header": null }, { "type": "code_execution_20260120", "category": "server", "beta_header": null }, { "type": "code_execution_20250825", "category": "server", "beta_header": null }, { "type": "tool_search_tool_regex_20251119", "category": "server", "beta_header": null }, { "type": "tool_search_tool_bm25_20251119", "category": "server", "beta_header": null }, { "type": "advisor_20260301", "category": "server", "beta_header": "advisor-tool-2026-03-01" }, { "type": "mcp_toolset", "category": "mcp", "beta_header": "mcp-client-2025-11-20" }, { "type": "memory_20250818", "category": "client", "beta_header": null }, { "type": "bash_20250124", "category": "client", "beta_header": null }, { "type": "text_editor_20250728", "category": "client", "beta_header": null }, { "type": "computer_20250124", "category": "client", "beta_header": "computer-use-2025-01-24" } ], "endpoints": [ "POST /v1/messages", "POST /v1/messages/count_tokens", "POST /v1/messages/batches", "GET /v1/models/{model_id}", "Managed Agents (/v1/agents, /v1/sessions) — see managed-agents docs for per-model support" ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "input": 3, "output": 15, "cache_write_5m": 3.75, "cache_write_1h": 6, "cache_read": 0.3, "batch_input": 1.5, "batch_output": 7.5, "batch_discount": 0.5, "long_context_over_200k": "n/a (200k context)", "inference_geo_us_multiplier": null, "priority_tier": "same token prices; capacity commitment, no longer sold", "cache_read_multiplier": 0.1, "tool_use_system_prompt_tokens": { "auto_or_none": 496, "any_or_tool": 588 } }, "rate_limits": { "class": "sonnet-4.x (shared 4.6/4.5)", "ref": "generated/fragments/rate-limits/anthropic-rate-limits.json", "doc": "https://platform.claude.com/docs/en/api/rate-limits" }, "beta_headers": [ "advisor-tool-2026-03-01", "computer-use-2025-01-24", "interleaved-thinking-2025-05-14", "mcp-client-2025-11-20" ], "restrictions": { "data_retention": null, "access": null, "tool_choice": null, "thinking_disable": null }, "availability": { "account": "available", "platforms": [ "Claude API", "Amazon Bedrock", "Google Cloud (Vertex AI)", "Microsoft Foundry", "Claude Platform on AWS" ], "cloud_ids": { "bedrock": [ "anthropic.claude-sonnet-4-5-20250929-v1:0" ], "vertex": "claude-sonnet-4-5@20250929", "foundry": "claude-sonnet-4-5", "claude_platform_on_aws": "claude-sonnet-4-5" }, "regions": "Claude API is global by default; inference_geo us/global on 4.6+; Bedrock/Vertex regional endpoints +10%" }, "deprecation": { "state": "Active (legacy)", "deprecated_on": null, "retirement": "not sooner than 2026-09-29", "replacement": null }, "discrepancies_live_vs_docs": [ "live max_input_tokens 1000000 != documented context window 200000" ], "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 200, "request_note": "GET /v1/models/claude-sonnet-4-5-20250929 -> 200" }, "sources": [ { "url": "https://platform.claude.com/docs/en/models/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/models/sonnet-4-5/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/api/models/list", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/thinking", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/effort", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/prompt-caching", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/context-windows", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-sonnet-4-5", "display_name": "Claude Sonnet 4.5 (alias)", "kind": "alias", "resolves_to": "claude-sonnet-4-5-20250929", "aliases": [], "snapshots": [ "claude-sonnet-4-5-20250929" ], "family": "Sonnet", "generation": "4.5", "description": "Convenience alias; GET /v1/models/claude-sonnet-4-5 resolves to claude-sonnet-4-5-20250929. Aliases exist only for pre-4.6 models.", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "release_date": "2025-09-29", "context_window": 200000, "max_output": 64000, "pricing": "same as claude-sonnet-4-5-20250929", "endpoints": [ "POST /v1/messages", "GET /v1/models/{model_id}" ], "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 200, "request_note": "GET /v1/models/claude-sonnet-4-5 -> id claude-sonnet-4-5-20250929" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/models/model-ids-and-versions", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/models/sonnet-4-5/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-haiku-4-5-20251001", "display_name": "Claude Haiku 4.5", "kind": "snapshot", "aliases": [ "claude-haiku-4-5" ], "snapshots": [ "claude-haiku-4-5-20251001" ], "family": "Haiku", "generation": "4.5", "description": "The fastest model with near-frontier intelligence", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "lifecycle_docs": "Active (latest)", "release_date": "2025-10-15", "created_at_live": "2025-10-15T00:00:00Z", "knowledge_cutoff": { "reliable": "Feb 2025", "training_data": "Jul 2025" }, "context_window": 200000, "context_window_note": "200k", "max_output": 64000, "max_output_batch_beta": null, "live_max_input_tokens": 200000, "live_max_tokens": 64000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "thinking": "extended (manual)", "capabilities": { "text_input": true, "vision": true, "pdf_input": true, "high_resolution_vision_2576px": false, "tool_use": true, "parallel_tool_use": true, "tool_choice_any_or_tool": true, "strict_tool_use": true, "structured_outputs_json": true, "fine_grained_tool_streaming": true, "thinking_extended_manual_budget": true, "thinking_adaptive": false, "thinking_always_on": false, "thinking_on_by_default": false, "thinking_can_be_disabled": true, "interleaved_thinking": false, "thinking_display_omitted_default": false, "progress_updates_between_tool_calls": false, "effort_parameter": false, "effort_levels": [], "effort_default": null, "per_message_effort_beta": false, "fast_mode_speed_fast": false, "prompt_caching": true, "prompt_caching_1h_ttl": true, "automatic_caching_top_level_cache_control": true, "min_cacheable_tokens": 4096, "batch_api": true, "batch_extended_output_300k_beta": false, "citations": true, "files_api": true, "web_search": true, "web_search_dynamic_filtering": false, "web_fetch": true, "web_fetch_dynamic_filtering": false, "code_execution": false, "code_execution_docs": true, "programmatic_tool_calling": false, "computer_use": true, "computer_use_toolset_ga": false, "browser_use": false, "memory_tool": true, "text_editor_tool": true, "bash_tool": true, "tool_search": true, "advisor_tool": true, "mcp_connector": true, "agent_skills": true, "context_editing_clear_tool_uses": true, "context_editing_clear_thinking": true, "compaction_server_side": false, "compact_on_demand_beta": false, "context_1m_default_no_beta": false, "inference_geo_data_residency": false, "mid_conversation_system_messages": false, "mid_conversation_tool_changes_beta": false, "task_budgets_beta": false, "sampling_params_temperature_top_p_top_k": "accepted (incompatible with thinking on)", "assistant_prefill": "unknown", "priority_tier": true, "zero_data_retention_eligible": true, "tokenizer": "previous tokenizer", "multilingual": true, "latency_class": "Fastest", "output_modalities": [ "text" ] }, "live_capabilities": { "batch": { "supported": true }, "citations": { "supported": true }, "code_execution": { "supported": false }, "context_management": { "supported": true, "clear_tool_uses_20250919": { "supported": true }, "clear_thinking_20251015": { "supported": true }, "compact_20260112": { "supported": false } }, "effort": { "supported": false, "low": { "supported": false }, "medium": { "supported": false }, "high": { "supported": false }, "xhigh": { "supported": false }, "max": { "supported": false } }, "image_input": { "supported": true }, "pdf_input": { "supported": true }, "structured_outputs": { "supported": true }, "thinking": { "supported": true, "types": { "enabled": { "supported": true }, "adaptive": { "supported": false } } } }, "tools": [ { "type": "web_search_20250305", "category": "server", "beta_header": null }, { "type": "web_fetch_20250910", "category": "server", "beta_header": null }, { "type": "code_execution_20260521", "category": "server", "beta_header": null, "note": "Haiku 4.5: no programmatic tool calling / REPL persistence" }, { "type": "code_execution_20260120", "category": "server", "beta_header": null, "note": "Haiku 4.5: no programmatic tool calling / REPL persistence" }, { "type": "code_execution_20250825", "category": "server", "beta_header": null }, { "type": "tool_search_tool_regex_20251119", "category": "server", "beta_header": null }, { "type": "tool_search_tool_bm25_20251119", "category": "server", "beta_header": null }, { "type": "advisor_20260301", "category": "server", "beta_header": "advisor-tool-2026-03-01" }, { "type": "mcp_toolset", "category": "mcp", "beta_header": "mcp-client-2025-11-20" }, { "type": "memory_20250818", "category": "client", "beta_header": null }, { "type": "bash_20250124", "category": "client", "beta_header": null }, { "type": "text_editor_20250728", "category": "client", "beta_header": null }, { "type": "computer_20250124", "category": "client", "beta_header": "computer-use-2025-01-24" } ], "endpoints": [ "POST /v1/messages", "POST /v1/messages/count_tokens", "POST /v1/messages/batches", "GET /v1/models/{model_id}", "Managed Agents (/v1/agents, /v1/sessions) — see managed-agents docs for per-model support" ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "input": 1, "output": 5, "cache_write_5m": 1.25, "cache_write_1h": 2, "cache_read": 0.1, "batch_input": 0.5, "batch_output": 2.5, "batch_discount": 0.5, "long_context_over_200k": "n/a (200k context)", "inference_geo_us_multiplier": null, "priority_tier": "same token prices; capacity commitment, no longer sold", "cache_read_multiplier": 0.1, "tool_use_system_prompt_tokens": { "auto_or_none": 496, "any_or_tool": 588 } }, "rate_limits": { "class": "haiku-4.5", "ref": "generated/fragments/rate-limits/anthropic-rate-limits.json", "doc": "https://platform.claude.com/docs/en/api/rate-limits" }, "beta_headers": [ "advisor-tool-2026-03-01", "computer-use-2025-01-24", "mcp-client-2025-11-20" ], "restrictions": { "data_retention": null, "access": null, "tool_choice": null, "thinking_disable": null }, "availability": { "account": "available", "platforms": [ "Claude API", "Amazon Bedrock", "Google Cloud (Vertex AI)", "Microsoft Foundry", "Claude Platform on AWS" ], "cloud_ids": { "bedrock": [ "anthropic.claude-haiku-4-5", "anthropic.claude-haiku-4-5-20251001-v1:0" ], "vertex": "claude-haiku-4-5@20251001", "foundry": "claude-haiku-4-5", "claude_platform_on_aws": "claude-haiku-4-5" }, "regions": "Claude API is global by default; inference_geo us/global on 4.6+; Bedrock/Vertex regional endpoints +10%" }, "deprecation": { "state": "Active (latest)", "deprecated_on": null, "retirement": "not sooner than 2026-10-15", "replacement": null }, "discrepancies_live_vs_docs": [ "live capabilities.code_execution.supported=false while code-execution-tool docs list claude-haiku-4-5-20251001 as supported (without PTC/REPL persistence)" ], "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 200, "request_note": "GET /v1/models/claude-haiku-4-5-20251001 -> 200" }, "sources": [ { "url": "https://platform.claude.com/docs/en/models/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/models/haiku-4-5/overview", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/api/models/list", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/thinking", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/effort", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/prompt-caching", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/context-windows", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-haiku-4-5", "display_name": "Claude Haiku 4.5 (alias)", "kind": "alias", "resolves_to": "claude-haiku-4-5-20251001", "aliases": [], "snapshots": [ "claude-haiku-4-5-20251001" ], "family": "Haiku", "generation": "4.5", "description": "Convenience alias; GET /v1/models/claude-haiku-4-5 resolves to claude-haiku-4-5-20251001. Aliases exist only for pre-4.6 models.", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "release_date": "2025-10-15", "context_window": 200000, "max_output": 64000, "pricing": "same as claude-haiku-4-5-20251001", "endpoints": [ "POST /v1/messages", "GET /v1/models/{model_id}" ], "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 200, "request_note": "GET /v1/models/claude-haiku-4-5 -> id claude-haiku-4-5-20251001" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/models/model-ids-and-versions", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/models/haiku-4-5/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-opus-4-1-20250805", "display_name": "Claude Opus 4.1", "kind": "snapshot", "aliases": [ "claude-opus-4-1" ], "snapshots": [ "claude-opus-4-1-20250805" ], "family": "Opus", "generation": "4.1", "status": [ "DOCUMENTED", "RETIRED", "LIVE_VERIFIED" ], "lifecycle_docs": "Retired", "release_date": "2025-08-05", "knowledge_cutoff": null, "context_window": 200000, "max_output": 32000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "note": "retired; capability matrix not maintained in current docs", "computer_use_computer_20250124": true, "min_cacheable_tokens": 1024 }, "tools": [ { "type": "computer_20250124", "category": "client", "beta_header": "computer-use-2025-01-24" } ], "endpoints": [], "pricing": { "currency": "USD", "unit": "per 1M tokens", "input": 15, "output": 75, "cache_write_5m": 18.75, "cache_write_1h": 30, "cache_read": 1.5, "batch_input": 7.5, "batch_output": 37.5, "batch_discount": 0.5, "long_context_over_200k": "n/a (200k context)", "inference_geo_us_multiplier": null, "priority_tier": "same token prices; capacity commitment, no longer sold", "cache_read_multiplier": 0.1, "tool_use_system_prompt_tokens": { "auto_or_none": 313, "any_or_tool": 315 } }, "pricing_note": null, "availability": { "account": "retired on Claude API (404 not_found_error)", "cloud_ids": { "bedrock": [ "anthropic.claude-opus-4-1-20250805-v1:0" ], "vertex": "claude-opus-4-1@20250805" }, "cloud_note": "retired on Claude API; still listed (deprecated) on Bedrock and Google Cloud" }, "deprecation": { "state": "Retired", "deprecated_on": "2026-06-05", "retired_on": "2026-08-05", "replacement": "claude-opus-4-8" }, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 404, "request_note": "GET /v1/models/claude-opus-4-1-20250805 -> 404 {\"type\": \"error\", \"error\": {\"type\": \"not_found_error\", \"message\": \"model: claude-opus-4-1-20250805\"}, \"request_id\": \"req" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/release-notes/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-opus-4-20250514", "display_name": "Claude Opus 4", "kind": "snapshot", "aliases": [ "claude-opus-4-0" ], "snapshots": [ "claude-opus-4-20250514" ], "family": "Opus", "generation": "4", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Retired", "release_date": "2025-05-22", "knowledge_cutoff": null, "context_window": 200000, "max_output": 32000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "note": "retired; capability matrix not maintained in current docs", "computer_use_computer_20250124": true, "min_cacheable_tokens": 1024 }, "tools": [ { "type": "computer_20250124", "category": "client", "beta_header": "computer-use-2025-01-24" } ], "endpoints": [], "pricing": { "currency": "USD", "unit": "per 1M tokens", "input": 15, "output": 75, "cache_write_5m": 18.75, "cache_write_1h": 30, "cache_read": 1.5, "batch_input": 7.5, "batch_output": 37.5, "batch_discount": 0.5, "long_context_over_200k": "n/a (200k context)", "inference_geo_us_multiplier": null, "priority_tier": "same token prices; capacity commitment, no longer sold", "cache_read_multiplier": 0.1, "tool_use_system_prompt_tokens": { "auto_or_none": 313, "any_or_tool": 315 } }, "pricing_note": null, "availability": { "account": "retired (not probed)", "cloud_ids": { "bedrock": [ "anthropic.claude-opus-4-20250514-v1:0" ], "vertex": "claude-opus-4@20250514" }, "cloud_note": "retired on Claude API and Bedrock; still listed (deprecated) on Google Cloud" }, "deprecation": { "state": "Retired", "deprecated_on": "2026-04-14", "retired_on": "2026-06-15", "replacement": "claude-opus-4-8" }, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-19T01:44:33Z", "result": "n/a", "http_status": null, "request_note": "not probed" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/release-notes/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-sonnet-4-20250514", "display_name": "Claude Sonnet 4", "kind": "snapshot", "aliases": [ "claude-sonnet-4-0" ], "snapshots": [ "claude-sonnet-4-20250514" ], "family": "Sonnet", "generation": "4", "status": [ "DOCUMENTED", "RETIRED", "LIVE_VERIFIED" ], "lifecycle_docs": "Retired", "release_date": "2025-05-22", "knowledge_cutoff": null, "context_window": 200000, "max_output": 64000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "note": "retired; capability matrix not maintained in current docs", "computer_use_computer_20250124": true, "min_cacheable_tokens": 1024 }, "tools": [ { "type": "computer_20250124", "category": "client", "beta_header": "computer-use-2025-01-24" } ], "endpoints": [], "pricing": { "currency": "USD", "unit": "per 1M tokens", "input": 3, "output": 15, "cache_write_5m": 3.75, "cache_write_1h": 6, "cache_read": 0.3, "batch_input": 1.5, "batch_output": 7.5, "batch_discount": 0.5, "long_context_over_200k": "n/a (200k context)", "inference_geo_us_multiplier": null, "priority_tier": "same token prices; capacity commitment, no longer sold", "cache_read_multiplier": 0.1, "tool_use_system_prompt_tokens": { "auto_or_none": 313, "any_or_tool": 315 } }, "pricing_note": null, "availability": { "account": "retired on Claude API (404 not_found_error)", "cloud_ids": { "bedrock": [ "anthropic.claude-sonnet-4-20250514-v1:0" ], "vertex": "claude-sonnet-4@20250514" }, "cloud_note": "retired on Claude API; still listed (deprecated) on Bedrock and Google Cloud; 1M context beta retired 2026-04-30" }, "deprecation": { "state": "Retired", "deprecated_on": "2026-04-14", "retired_on": "2026-06-15", "replacement": "claude-sonnet-4-6" }, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 404, "request_note": "GET /v1/models/claude-sonnet-4-20250514 -> 404 {\"type\": \"error\", \"error\": {\"type\": \"not_found_error\", \"message\": \"model: claude-sonnet-4-20250514\"}, \"request_id\": \"req" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/release-notes/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-3-7-sonnet-20250219", "display_name": "Claude Sonnet 3.7", "kind": "snapshot", "aliases": [ "claude-3-7-sonnet-latest" ], "snapshots": [ "claude-3-7-sonnet-20250219" ], "family": "Sonnet", "generation": "3.7", "status": [ "DOCUMENTED", "RETIRED", "LIVE_VERIFIED" ], "lifecycle_docs": "Retired", "release_date": "2025-02-24", "knowledge_cutoff": null, "context_window": 200000, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "note": "retired; capability matrix not maintained in current docs", "computer_use_computer_20250124": false, "min_cacheable_tokens": null }, "tools": [], "endpoints": [], "pricing": null, "pricing_note": "not listed on the current pricing page", "availability": { "account": "retired on Claude API (404 not_found_error)", "cloud_ids": { "bedrock": [ "anthropic.claude-3-7-sonnet-20250219-v1:0" ], "vertex": null }, "cloud_note": "retired everywhere per Bedrock table" }, "deprecation": { "state": "Retired", "deprecated_on": "2025-10-28", "retired_on": "2026-02-19", "replacement": "claude-sonnet-4-6" }, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 404, "request_note": "GET /v1/models/claude-3-7-sonnet-20250219 -> 404 {\"type\": \"error\", \"error\": {\"type\": \"not_found_error\", \"message\": \"model: claude-3-7-sonnet-20250219\"}, \"request_id\": \"r" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/release-notes/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-3-5-haiku-20241022", "display_name": "Claude Haiku 3.5", "kind": "snapshot", "aliases": [ "claude-3-5-haiku-latest" ], "snapshots": [ "claude-3-5-haiku-20241022" ], "family": "Haiku", "generation": "3.5", "status": [ "DOCUMENTED", "RETIRED", "LIVE_VERIFIED" ], "lifecycle_docs": "Retired", "release_date": "2024-11-04", "knowledge_cutoff": null, "context_window": 200000, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "note": "retired; capability matrix not maintained in current docs", "computer_use_computer_20250124": false, "min_cacheable_tokens": 2048 }, "tools": [], "endpoints": [], "pricing": { "currency": "USD", "unit": "per 1M tokens", "input": 0.8, "output": 4, "cache_write_5m": 1.0, "cache_write_1h": 1.6, "cache_read": 0.08, "batch_input": 0.4, "batch_output": 2.0, "batch_discount": 0.5, "long_context_over_200k": "n/a (200k context)", "inference_geo_us_multiplier": null, "priority_tier": "same token prices; capacity commitment, no longer sold", "cache_read_multiplier": 0.1, "tool_use_system_prompt_tokens": { "auto_or_none": 264, "any_or_tool": 355 } }, "pricing_note": null, "availability": { "account": "retired on Claude API (404 not_found_error)", "cloud_ids": { "bedrock": [ "anthropic.claude-3-5-haiku-20241022-v1:0" ], "vertex": "claude-3-5-haiku@20241022" }, "cloud_note": "retired on Claude API; still listed (deprecated) on Bedrock and Google Cloud; counts cache reads toward ITPM" }, "deprecation": { "state": "Retired", "deprecated_on": "2025-12-19", "retired_on": "2026-02-19", "replacement": "claude-haiku-4-5-20251001" }, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 404, "request_note": "GET /v1/models/claude-3-5-haiku-20241022 -> 404 {\"type\": \"error\", \"error\": {\"type\": \"not_found_error\", \"message\": \"model: claude-3-5-haiku-20241022\"}, \"request_id\": \"re" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/release-notes/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-3-haiku-20240307", "display_name": "Claude Haiku 3", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-3-haiku-20240307" ], "family": "Haiku", "generation": "3", "status": [ "DOCUMENTED", "RETIRED", "LIVE_VERIFIED" ], "lifecycle_docs": "Retired", "release_date": "2024-03-07", "knowledge_cutoff": null, "context_window": 200000, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "note": "retired; capability matrix not maintained in current docs", "computer_use_computer_20250124": false, "min_cacheable_tokens": null }, "tools": [], "endpoints": [], "pricing": null, "pricing_note": "not listed on the current pricing page", "availability": { "account": "retired on Claude API (404 not_found_error)", "cloud_ids": { "bedrock": null, "vertex": null }, "cloud_note": null }, "deprecation": { "state": "Retired", "deprecated_on": "2026-02-19", "retired_on": "2026-04-20", "replacement": "claude-haiku-4-5-20251001" }, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 404, "request_note": "GET /v1/models/claude-3-haiku-20240307 -> 404 {\"type\": \"error\", \"error\": {\"type\": \"not_found_error\", \"message\": \"model: claude-3-haiku-20240307\"}, \"request_id\": \"req_" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/release-notes/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-3-5-sonnet-20241022", "display_name": "Claude Sonnet 3.5 (Oct 2024)", "kind": "snapshot", "aliases": [ "claude-3-5-sonnet-latest" ], "snapshots": [ "claude-3-5-sonnet-20241022" ], "family": "Sonnet", "generation": "3.5", "status": [ "DOCUMENTED", "RETIRED", "LIVE_VERIFIED" ], "lifecycle_docs": "Retired", "release_date": "2024-10-22", "knowledge_cutoff": null, "context_window": 200000, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "note": "retired; capability matrix not maintained in current docs", "computer_use_computer_20250124": false, "min_cacheable_tokens": null }, "tools": [], "endpoints": [], "pricing": null, "pricing_note": "not listed on the current pricing page", "availability": { "account": "retired on Claude API (404 not_found_error)", "cloud_ids": { "bedrock": null, "vertex": null }, "cloud_note": null }, "deprecation": { "state": "Retired", "deprecated_on": "2025-08-13", "retired_on": "2025-10-28", "replacement": "claude-sonnet-4-6" }, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 404, "request_note": "GET /v1/models/claude-3-5-sonnet-20241022 -> 404 {\"type\": \"error\", \"error\": {\"type\": \"not_found_error\", \"message\": \"model: claude-3-5-sonnet-20241022\"}, \"request_id\": \"r" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/release-notes/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-3-5-sonnet-20240620", "display_name": "Claude Sonnet 3.5 (Jun 2024)", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-3-5-sonnet-20240620" ], "family": "Sonnet", "generation": "3.5", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Retired", "release_date": "2024-06-20", "knowledge_cutoff": null, "context_window": 200000, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "note": "retired; capability matrix not maintained in current docs", "computer_use_computer_20250124": false, "min_cacheable_tokens": null }, "tools": [], "endpoints": [], "pricing": null, "pricing_note": "not listed on the current pricing page", "availability": { "account": "retired (not probed)", "cloud_ids": { "bedrock": null, "vertex": null }, "cloud_note": null }, "deprecation": { "state": "Retired", "deprecated_on": "2025-08-13", "retired_on": "2025-10-28", "replacement": "claude-sonnet-4-6" }, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-19T01:44:33Z", "result": "n/a", "http_status": null, "request_note": "not probed" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/release-notes/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-3-opus-20240229", "display_name": "Claude Opus 3", "kind": "snapshot", "aliases": [ "claude-3-opus-latest" ], "snapshots": [ "claude-3-opus-20240229" ], "family": "Opus", "generation": "3", "status": [ "DOCUMENTED", "RETIRED", "LIVE_VERIFIED" ], "lifecycle_docs": "Retired", "release_date": "2024-02-29", "knowledge_cutoff": null, "context_window": 200000, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "note": "retired; capability matrix not maintained in current docs", "computer_use_computer_20250124": false, "min_cacheable_tokens": null }, "tools": [], "endpoints": [], "pricing": null, "pricing_note": "not listed on the current pricing page", "availability": { "account": "retired on Claude API (404 not_found_error)", "cloud_ids": { "bedrock": null, "vertex": null }, "cloud_note": "researchers may request access via External Researcher Access Program" }, "deprecation": { "state": "Retired", "deprecated_on": "2025-06-30", "retired_on": "2026-01-05", "replacement": "claude-opus-4-8" }, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-19T01:44:33Z", "result": "success", "http_status": 404, "request_note": "GET /v1/models/claude-3-opus-20240229 -> 404 {\"type\": \"error\", \"error\": {\"type\": \"not_found_error\", \"message\": \"model: claude-3-opus-20240229\"}, \"request_id\": \"req_0" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/release-notes/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-3-sonnet-20240229", "display_name": "Claude Sonnet 3", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-3-sonnet-20240229" ], "family": "Sonnet", "generation": "3", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Retired", "release_date": "2024-02-29", "knowledge_cutoff": null, "context_window": 200000, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "note": "retired; capability matrix not maintained in current docs", "computer_use_computer_20250124": false, "min_cacheable_tokens": null }, "tools": [], "endpoints": [], "pricing": null, "pricing_note": "not listed on the current pricing page", "availability": { "account": "retired (not probed)", "cloud_ids": { "bedrock": null, "vertex": null }, "cloud_note": null }, "deprecation": { "state": "Retired", "deprecated_on": "2025-01-21", "retired_on": "2025-07-21", "replacement": "claude-sonnet-4-6" }, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-19T01:44:33Z", "result": "n/a", "http_status": null, "request_note": "not probed" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/release-notes/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-2.1", "display_name": "Claude 2.1", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-2.1" ], "family": "Claude 2", "generation": "2.1", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Retired", "release_date": null, "knowledge_cutoff": null, "context_window": 200000, "max_output": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "note": "retired; capability matrix not maintained in current docs", "computer_use_computer_20250124": false, "min_cacheable_tokens": null }, "tools": [], "endpoints": [], "pricing": null, "pricing_note": "not listed on the current pricing page", "availability": { "account": "retired (not probed)", "cloud_ids": { "bedrock": null, "vertex": null }, "cloud_note": null }, "deprecation": { "state": "Retired", "deprecated_on": "2025-01-21", "retired_on": "2025-07-21", "replacement": "claude-opus-4-8" }, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-19T01:44:33Z", "result": "n/a", "http_status": null, "request_note": "not probed" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/release-notes/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-2.0", "display_name": "Claude 2.0", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-2.0" ], "family": "Claude 2", "generation": "2.0", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Retired", "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "note": "retired; capability matrix not maintained in current docs", "computer_use_computer_20250124": false, "min_cacheable_tokens": null }, "tools": [], "endpoints": [], "pricing": null, "pricing_note": "not listed on the current pricing page", "availability": { "account": "retired (not probed)", "cloud_ids": { "bedrock": null, "vertex": null }, "cloud_note": null }, "deprecation": { "state": "Retired", "deprecated_on": "2025-01-21", "retired_on": "2025-07-21", "replacement": "claude-opus-4-8" }, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-19T01:44:33Z", "result": "n/a", "http_status": null, "request_note": "not probed" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/release-notes/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-1.0", "display_name": "claude-1.0", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-1.0" ], "family": "Claude 1 / Instant", "generation": "1.0", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Retired", "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "note": "retired; capability matrix not maintained in current docs", "computer_use_computer_20250124": false, "min_cacheable_tokens": null }, "tools": [], "endpoints": [], "pricing": null, "pricing_note": "not listed on the current pricing page", "availability": { "account": "retired (not probed)", "cloud_ids": { "bedrock": null, "vertex": null }, "cloud_note": null }, "deprecation": { "state": "Retired", "deprecated_on": "2024-09-04", "retired_on": "2024-11-06", "replacement": "claude-haiku-4-5-20251001" }, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-19T01:44:33Z", "result": "n/a", "http_status": null, "request_note": "not probed" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/release-notes/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-1.1", "display_name": "claude-1.1", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-1.1" ], "family": "Claude 1 / Instant", "generation": "1.1", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Retired", "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "note": "retired; capability matrix not maintained in current docs", "computer_use_computer_20250124": false, "min_cacheable_tokens": null }, "tools": [], "endpoints": [], "pricing": null, "pricing_note": "not listed on the current pricing page", "availability": { "account": "retired (not probed)", "cloud_ids": { "bedrock": null, "vertex": null }, "cloud_note": null }, "deprecation": { "state": "Retired", "deprecated_on": "2024-09-04", "retired_on": "2024-11-06", "replacement": "claude-haiku-4-5-20251001" }, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-19T01:44:33Z", "result": "n/a", "http_status": null, "request_note": "not probed" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/release-notes/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-1.2", "display_name": "claude-1.2", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-1.2" ], "family": "Claude 1 / Instant", "generation": "1.2", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Retired", "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "note": "retired; capability matrix not maintained in current docs", "computer_use_computer_20250124": false, "min_cacheable_tokens": null }, "tools": [], "endpoints": [], "pricing": null, "pricing_note": "not listed on the current pricing page", "availability": { "account": "retired (not probed)", "cloud_ids": { "bedrock": null, "vertex": null }, "cloud_note": null }, "deprecation": { "state": "Retired", "deprecated_on": "2024-09-04", "retired_on": "2024-11-06", "replacement": "claude-haiku-4-5-20251001" }, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-19T01:44:33Z", "result": "n/a", "http_status": null, "request_note": "not probed" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/release-notes/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-1.3", "display_name": "claude-1.3", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-1.3" ], "family": "Claude 1 / Instant", "generation": "1.3", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Retired", "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "note": "retired; capability matrix not maintained in current docs", "computer_use_computer_20250124": false, "min_cacheable_tokens": null }, "tools": [], "endpoints": [], "pricing": null, "pricing_note": "not listed on the current pricing page", "availability": { "account": "retired (not probed)", "cloud_ids": { "bedrock": null, "vertex": null }, "cloud_note": null }, "deprecation": { "state": "Retired", "deprecated_on": "2024-09-04", "retired_on": "2024-11-06", "replacement": "claude-haiku-4-5-20251001" }, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-19T01:44:33Z", "result": "n/a", "http_status": null, "request_note": "not probed" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/release-notes/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-instant-1.0", "display_name": "claude-instant-1.0", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-instant-1.0" ], "family": "Claude 1 / Instant", "generation": "1.0", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Retired", "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "note": "retired; capability matrix not maintained in current docs", "computer_use_computer_20250124": false, "min_cacheable_tokens": null }, "tools": [], "endpoints": [], "pricing": null, "pricing_note": "not listed on the current pricing page", "availability": { "account": "retired (not probed)", "cloud_ids": { "bedrock": null, "vertex": null }, "cloud_note": null }, "deprecation": { "state": "Retired", "deprecated_on": "2024-09-04", "retired_on": "2024-11-06", "replacement": "claude-haiku-4-5-20251001" }, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-19T01:44:33Z", "result": "n/a", "http_status": null, "request_note": "not probed" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/release-notes/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-instant-1.1", "display_name": "claude-instant-1.1", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-instant-1.1" ], "family": "Claude 1 / Instant", "generation": "1.1", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Retired", "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "note": "retired; capability matrix not maintained in current docs", "computer_use_computer_20250124": false, "min_cacheable_tokens": null }, "tools": [], "endpoints": [], "pricing": null, "pricing_note": "not listed on the current pricing page", "availability": { "account": "retired (not probed)", "cloud_ids": { "bedrock": null, "vertex": null }, "cloud_note": null }, "deprecation": { "state": "Retired", "deprecated_on": "2024-09-04", "retired_on": "2024-11-06", "replacement": "claude-haiku-4-5-20251001" }, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-19T01:44:33Z", "result": "n/a", "http_status": null, "request_note": "not probed" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/release-notes/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "anthropic", "id": "claude-instant-1.2", "display_name": "claude-instant-1.2", "kind": "snapshot", "aliases": [], "snapshots": [ "claude-instant-1.2" ], "family": "Claude 1 / Instant", "generation": "1.2", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Retired", "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "note": "retired; capability matrix not maintained in current docs", "computer_use_computer_20250124": false, "min_cacheable_tokens": null }, "tools": [], "endpoints": [], "pricing": null, "pricing_note": "not listed on the current pricing page", "availability": { "account": "retired (not probed)", "cloud_ids": { "bedrock": null, "vertex": null }, "cloud_note": null }, "deprecation": { "state": "Retired", "deprecated_on": "2024-09-04", "retired_on": "2024-11-06", "replacement": "claude-haiku-4-5-20251001" }, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-19T01:44:33Z", "result": "n/a", "http_status": null, "request_note": "not probed" }, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://platform.claude.com/docs/en/release-notes/overview", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/anthropic-models.json" }, { "provider": "gemini", "id": "gemini-2.5-flash", "display_name": "Gemini 2.5 Flash", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini 2.5", "generation": "2.5", "description": "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.", "status": [ "DOCUMENTED", "LIVE_DISCOVERED" ], "lifecycle_docs": "Stable (GA)", "release_date": "2025-06-17", "knowledge_cutoff": "January 2025", "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": 1048576, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "thinking": "on (dynamic budget)", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "on (dynamic budget)", "thinking_levels": [ "low", "medium", "high" ], "thinking_level_param": false, "thinking_budget_legacy_param": true, "thought_signatures": false, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": true, "url_context": true, "code_execution": true, "computer_use": false, "file_search": true, "context_caching_explicit": true, "context_caching_docs": true, "context_caching_implicit": true, "batch_api": true, "batch_api_docs": true, "flex_inference": true, "priority_inference": true, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": true, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": [ 3000000, 400000000, 1000000000 ] }, "live_model_metadata": { "name": "models/gemini-2.5-flash", "version": "001", "displayName": "Gemini 2.5 Flash", "description": "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-2.5-flash:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-2.5-flash:countTokens", "source": "live supportedGenerationMethods" }, { "name": "createCachedContent", "route": "POST /v1beta/cachedContents (model=models/gemini-2.5-flash)", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-2.5-flash:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-2.5-flash:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-2.5-flash)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "google_maps", "category": "server", "support": true }, { "type": "url_context", "category": "server", "support": true }, { "type": "code_execution", "category": "server", "support": true }, { "type": "file_search", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "tiers": { "standard": { "input": 0.3, "audio_input": 1.0, "output": 2.5, "cached_input": 0.03, "cached_audio_input": 0.1, "cache_storage_hour": 1.0 }, "batch": { "input": 0.15, "audio_input": 0.5, "output": 1.25, "cached_input": 0.03, "cached_audio_input": 0.1, "cache_storage_hour": 1.0 }, "flex": { "input": 0.15, "audio_input": 0.5, "output": 1.25, "cached_input": 0.03, "cached_audio_input": 0.1, "cache_storage_hour": 1.0 }, "priority": { "input": 0.54, "audio_input": 1.8, "output": 4.5, "cached_input": 0.054, "cached_audio_input": 0.18, "cache_storage_hour": 1.8 } }, "free_tier": "input/output free of charge; caching not available; Google Search grounding free up to 500 RPD (shared with Flash-Lite)", "grounding": { "google_search": "1,500 RPD free (limit shared Flash/Flash-Lite), then $35 per 1,000 grounded prompts; free tier: 500 RPD", "google_maps": "1,500 RPD free, then $25 per 1,000 grounded prompts; free tier 500 RPD" }, "output_includes_thinking_tokens": true, "batch_discount": 0.5, "flex_discount": 0.5, "priority_premium": "1.8x standard (docs: 75-100% more)" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 3000000, "Tier 2": 400000000, "Tier 3": 1000000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "input/output free of charge; caching not available; Google Search grounding free up to 500 RPD (shared with Flash-Lite)", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Stable: `gemini-2.5-flash` - Shut down: `gemini-2.5-flash-preview-09-2025`", "docs_latest_update": "June 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.5-pro", "display_name": "Gemini 2.5 Pro", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini 2.5", "generation": "2.5", "description": "Stable release (June 17th, 2025) of Gemini 2.5 Pro", "status": [ "DOCUMENTED", "LIVE_DISCOVERED" ], "lifecycle_docs": "Stable (GA)", "release_date": "2025-06-17", "knowledge_cutoff": "January 2025", "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": 1048576, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "thinking": "on (dynamic budget)", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": true, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "on (dynamic budget)", "thinking_levels": [ "low", "medium", "high" ], "thinking_level_param": false, "thinking_budget_legacy_param": true, "thought_signatures": false, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": true, "url_context": true, "code_execution": true, "computer_use": false, "file_search": true, "context_caching_explicit": true, "context_caching_docs": true, "context_caching_implicit": true, "batch_api": true, "batch_api_docs": true, "flex_inference": true, "priority_inference": true, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": true, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": [ 5000000, 500000000, 1000000000 ] }, "live_model_metadata": { "name": "models/gemini-2.5-pro", "version": "2.5", "displayName": "Gemini 2.5 Pro", "description": "Stable release (June 17th, 2025) of Gemini 2.5 Pro", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-2.5-pro:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-2.5-pro:countTokens", "source": "live supportedGenerationMethods" }, { "name": "createCachedContent", "route": "POST /v1beta/cachedContents (model=models/gemini-2.5-pro)", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-2.5-pro:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-2.5-pro:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-2.5-pro)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "google_maps", "category": "server", "support": true }, { "type": "url_context", "category": "server", "support": true }, { "type": "code_execution", "category": "server", "support": true }, { "type": "file_search", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "tiers": { "standard": { "input": 1.25, "input_over_200k": 2.5, "output": 10.0, "output_over_200k": 15.0, "cached_input": 0.125, "cached_input_over_200k": 0.25, "cache_storage_hour": 4.5 }, "batch": { "input": 0.625, "input_over_200k": 1.25, "output": 5.0, "output_over_200k": 7.5, "cached_input": 0.125, "cached_input_over_200k": 0.25, "cache_storage_hour": 4.5 }, "flex": { "input": 0.625, "input_over_200k": 1.25, "output": 5.0, "output_over_200k": 7.5, "cached_input": 0.125, "cached_input_over_200k": 0.25, "cache_storage_hour": 4.5 }, "priority": { "input": 2.25, "input_over_200k": 4.5, "output": 18.0, "output_over_200k": 27.0, "cached_input": 0.225, "cached_input_over_200k": 0.45, "cache_storage_hour": 8.1 } }, "free_tier": "input/output free of charge (standard/priority rows); caching, Batch, Flex not available", "grounding": { "google_search": "1,500 RPD free, then $35 per 1,000 grounded prompts", "google_maps": "10,000 RPD free, then $25 per 1,000 grounded prompts" }, "output_includes_thinking_tokens": true, "batch_discount": 0.5, "flex_discount": 0.5, "priority_premium": "1.8x standard (docs: 75-100% more)", "long_context_threshold": 200000 }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 5000000, "Tier 2": 500000000, "Tier 3": 1000000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "input/output free of charge (standard/priority rows); caching, Batch, Flex not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-pro", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - `Stable: gemini-2.5-pro`", "docs_latest_update": "June 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.5-flash-preview-tts", "display_name": "Gemini 2.5 Flash Preview TTS", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 2.5", "generation": "2.5", "description": "Gemini 2.5 Flash Preview TTS", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW" ], "lifecycle_docs": "Preview", "release_date": "2025-05-20", "knowledge_cutoff": null, "context_window": 8192, "max_output": 16384, "docs_input_token_limit": 8192, "docs_output_token_limit": 16384, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "thinking": "not supported", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": false, "image_output": false, "audio_output": true, "video_output": false, "music_output": false, "embeddings": false, "thinking": false, "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": true, "thought_signatures": false, "structured_output": false, "function_calling": false, "parallel_function_calling": false, "compositional_function_calling": false, "google_search_grounding": false, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": true, "flex_inference": false, "priority_inference": false, "live_api": false, "tts": true, "audio_generation_docs": true, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": "unknown", "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": [ 100000, 100000, 4000000 ] }, "live_model_metadata": { "name": "models/gemini-2.5-flash-preview-tts", "version": "gemini-2.5-flash-exp-tts-2025-05-19", "displayName": "Gemini 2.5 Flash Preview TTS", "description": "Gemini 2.5 Flash Preview TTS", "inputTokenLimit": 8192, "outputTokenLimit": 16384, "supportedGenerationMethods": [ "countTokens", "generateContent" ], "thinking": null, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "countTokens", "generateContent" ], "endpoints": [ { "name": "countTokens", "route": "POST /v1beta/models/gemini-2.5-flash-preview-tts:countTokens", "source": "live supportedGenerationMethods" }, { "name": "generateContent", "route": "POST /v1beta/models/gemini-2.5-flash-preview-tts:generateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-2.5-flash-preview-tts:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-2.5-flash-preview-tts)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [], "pricing": { "currency": "USD", "input_text": 0.5, "output_audio": 10.0, "batch": { "input_text": 0.25, "output_audio": 5.0 }, "unit": "per 1M tokens", "free_tier": "free of charge (standard)" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 100000, "Tier 2": 100000, "Tier 3": 4000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "free of charge (standard)", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "docs: Batch API supported, but batchGenerateContent absent from live supportedGenerationMethods" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-preview-tts", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - `gemini-2.5-flash-preview-tts`", "docs_latest_update": "December 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.5-pro-preview-tts", "display_name": "Gemini 2.5 Pro Preview TTS", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 2.5", "generation": "2.5", "description": "Gemini 2.5 Pro Preview TTS", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW" ], "lifecycle_docs": "Preview", "release_date": "2025-05-20", "knowledge_cutoff": null, "context_window": 8192, "max_output": 16384, "docs_input_token_limit": 8192, "docs_output_token_limit": 16384, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "thinking": "not supported", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": false, "image_output": false, "audio_output": true, "video_output": false, "music_output": false, "embeddings": false, "thinking": false, "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": true, "thought_signatures": false, "structured_output": false, "function_calling": false, "parallel_function_calling": false, "compositional_function_calling": false, "google_search_grounding": false, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": true, "flex_inference": false, "priority_inference": false, "live_api": false, "tts": true, "audio_generation_docs": true, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": "unknown", "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": [ 25000, 100000, 1000000 ] }, "live_model_metadata": { "name": "models/gemini-2.5-pro-preview-tts", "version": "gemini-2.5-pro-preview-tts-2025-05-19", "displayName": "Gemini 2.5 Pro Preview TTS", "description": "Gemini 2.5 Pro Preview TTS", "inputTokenLimit": 8192, "outputTokenLimit": 16384, "supportedGenerationMethods": [ "countTokens", "generateContent", "batchGenerateContent" ], "thinking": null, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "countTokens", "generateContent", "batchGenerateContent" ], "endpoints": [ { "name": "countTokens", "route": "POST /v1beta/models/gemini-2.5-pro-preview-tts:countTokens", "source": "live supportedGenerationMethods" }, { "name": "generateContent", "route": "POST /v1beta/models/gemini-2.5-pro-preview-tts:generateContent", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-2.5-pro-preview-tts:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-2.5-pro-preview-tts:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-2.5-pro-preview-tts)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [], "pricing": { "currency": "USD", "input_text": 1.0, "output_audio": 20.0, "batch": { "input_text": 0.5, "output_audio": 10.0 }, "unit": "per 1M tokens", "free_tier": "not available" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 25000, "Tier 2": 100000, "Tier 3": 1000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-pro-preview-tts", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - `gemini-2.5-pro-preview-tts`", "docs_latest_update": "December 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemma-4-26b-a4b-it", "display_name": "Gemma 4 26B A4B IT", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemma 4", "generation": "4", "description": "Gemma 4 26B A4B IT", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "LIVE_VERIFIED" ], "lifecycle_docs": "Stable (GA)", "release_date": "2026-04-02", "knowledge_cutoff": null, "context_window": 262144, "max_output": 32768, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": true, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": "unknown", "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemma-4-26b-a4b-it", "version": "001", "displayName": "Gemma 4 26B A4B IT", "description": "Gemma 4 26B A4B IT", "inputTokenLimit": 262144, "outputTokenLimit": 32768, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemma-4-26b-a4b-it:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemma-4-26b-a4b-it:countTokens", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemma-4-26b-a4b-it:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemma-4-26b-a4b-it)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [], "pricing": { "currency": "USD", "free_tier": "free of charge (input, output, caching, storage)", "paid_tier": "not available", "tuning": "not available", "grounding": "not available", "same_as": "gemma-4" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "free of charge (input, output, caching, storage)", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "Gemma 4 not documented in models.md (only pricing.md + changelog); live thinking=true and probe returned thoughtsTokenCount=5" ], "last_verified": "2026-09-19", "verification": { "method": "live_api", "verified_at": "2026-09-19T00:00:00Z", "result": "success", "http_status": 200, "request_note": "GET /v1beta/models/gemma-4-26b-a4b-it -> 200; POST :generateContent -> 200 (modelVersion=gemma-4-26b-a4b-it)" }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "generate_content_probe": { "http_status": 200, "request": "generateContent 'Reply with OK.' maxOutputTokens=8", "modelVersion": "gemma-4-26b-a4b-it", "responseId_present": true, "finishReason": "MAX_TOKENS", "usageMetadata": { "promptTokenCount": 5, "totalTokenCount": 10, "promptTokensDetails": [ { "modality": "TEXT", "tokenCount": 5 } ], "thoughtsTokenCount": 5, "serviceTier": "standard" }, "thoughtSignature_present": false, "text": "The user wants me to", "response_headers": { "Server-Timing": "gfet4t7; dur=446" }, "header_names": [ "Accept-Ranges", "Alt-Svc", "Connection", "Content-Type", "Date", "Server", "Server-Timing", "Transfer-Encoding", "Vary", "X-Content-Type-Options", "X-Frame-Options", "X-Gemini-Service-Tier", "X-XSS-Protection" ] }, "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemma-4-31b-it", "display_name": "Gemma 4 31B IT", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemma 4", "generation": "4", "description": "Gemma 4 31B IT", "status": [ "DOCUMENTED", "LIVE_DISCOVERED" ], "lifecycle_docs": "Stable (GA)", "release_date": "2026-04-02", "knowledge_cutoff": null, "context_window": 262144, "max_output": 32768, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": true, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": "unknown", "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemma-4-31b-it", "version": "001", "displayName": "Gemma 4 31B IT", "description": "Gemma 4 31B IT", "inputTokenLimit": 262144, "outputTokenLimit": 32768, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemma-4-31b-it:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemma-4-31b-it:countTokens", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemma-4-31b-it:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemma-4-31b-it)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [], "pricing": { "currency": "USD", "free_tier": "free of charge (input, output, caching, storage)", "paid_tier": "not available", "tuning": "not available", "grounding": "not available", "same_as": "gemma-4" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "free of charge (input, output, caching, storage)", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "Gemma 4 not documented in models.md (only pricing.md + changelog); live thinking=true and probe returned thoughtsTokenCount=5" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-flash-latest", "display_name": "Gemini Flash Latest", "kind": "alias", "aliases": [ { "resolves_to_live": "gemini-3.8-flash", "evidence": "generateContent modelVersion=gemini-3.8-flash (2026-09-19)", "history": [ "2026-01-21 -> gemini-3-flash-preview", "2026-05-19 -> gemini-3.5-flash", "observed 2026-09-19 -> gemini-3.8-flash (not announced in changelog)" ], "alias": "gemini-flash-latest" } ], "snapshots": [], "family": "Gemini (latest alias)", "generation": null, "description": "Latest release of Gemini Flash", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "LIVE_VERIFIED" ], "lifecycle_docs": "Alias", "release_date": null, "knowledge_cutoff": null, "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": true, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": "unknown", "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemini-flash-latest", "version": "Gemini Flash Latest", "displayName": "Gemini Flash Latest", "description": "Latest release of Gemini Flash", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-flash-latest:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-flash-latest:countTokens", "source": "live supportedGenerationMethods" }, { "name": "createCachedContent", "route": "POST /v1beta/cachedContents (model=models/gemini-flash-latest)", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-flash-latest:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-flash-latest:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-flash-latest)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [], "pricing": "billed as the model the alias currently resolves to (see aliases)", "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "live version field holds the display name ('Gemini Flash Latest') instead of a version" ], "last_verified": "2026-09-19", "verification": { "method": "live_api", "verified_at": "2026-09-19T00:00:00Z", "result": "success", "http_status": 200, "request_note": "GET /v1beta/models/gemini-flash-latest -> 200; POST :generateContent -> 200 (modelVersion=gemini-3.8-flash)" }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "alias_policy": "hot-swapped with every new release of the variation; 2-week e-mail notice before breaking changes (models.md)", "generate_content_probe": { "http_status": 200, "request": "generateContent 'Reply with OK.' maxOutputTokens=8", "modelVersion": "gemini-3.8-flash", "responseId_present": true, "finishReason": "MAX_TOKENS", "usageMetadata": { "promptTokenCount": 5, "totalTokenCount": 10, "promptTokensDetails": [ { "modality": "TEXT", "tokenCount": 5 } ], "thoughtsTokenCount": 5, "serviceTier": "standard" }, "thoughtSignature_present": false, "text": "", "response_headers": { "Server-Timing": "gfet4t7; dur=2606" }, "header_names": [ "Accept-Ranges", "Alt-Svc", "Connection", "Content-Type", "Date", "Server", "Server-Timing", "Transfer-Encoding", "Vary", "X-Content-Type-Options", "X-Frame-Options", "X-Gemini-Service-Tier", "X-XSS-Protection" ] }, "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-flash-lite-latest", "display_name": "Gemini Flash-Lite Latest", "kind": "alias", "aliases": [ { "resolves_to_live": "unknown (not probed)", "evidence": "GET 200; description 'Latest release of Gemini Flash-Lite'", "history": [], "alias": "gemini-flash-lite-latest" } ], "snapshots": [], "family": "Gemini (latest alias)", "generation": null, "description": "Latest release of Gemini Flash-Lite", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "LIVE_VERIFIED" ], "lifecycle_docs": "Alias", "release_date": null, "knowledge_cutoff": null, "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": true, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": "unknown", "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemini-flash-lite-latest", "version": "Gemini Flash-Lite Latest", "displayName": "Gemini Flash-Lite Latest", "description": "Latest release of Gemini Flash-Lite", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-flash-lite-latest:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-flash-lite-latest:countTokens", "source": "live supportedGenerationMethods" }, { "name": "createCachedContent", "route": "POST /v1beta/cachedContents (model=models/gemini-flash-lite-latest)", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-flash-lite-latest:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-flash-lite-latest:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-flash-lite-latest)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [], "pricing": "billed as the model the alias currently resolves to (see aliases)", "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "live version field holds the display name ('Gemini Flash-Lite Latest') instead of a version" ], "last_verified": "2026-09-19", "verification": { "method": "live_api", "verified_at": "2026-09-19T00:00:00Z", "result": "success", "http_status": 200, "request_note": "GET /v1beta/models/gemini-flash-lite-latest -> 200" }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "alias_policy": "hot-swapped with every new release of the variation; 2-week e-mail notice before breaking changes (models.md)", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-pro-latest", "display_name": "Gemini Pro Latest", "kind": "alias", "aliases": [ { "resolves_to_live": "gemini-3.1-pro (quota dimension model=gemini-3.1-pro in the 429 body)", "evidence": "429 RESOURCE_EXHAUSTED free-tier limit 0, quotaDimensions.model=gemini-3.1-pro (2026-09-19)", "history": [ "2026-01-21 -> gemini-3-pro-preview", "2026-03-09 gemini-3-pro-preview shut down -> points to gemini-3.1-pro-preview" ], "alias": "gemini-pro-latest" } ], "snapshots": [], "family": "Gemini (latest alias)", "generation": null, "description": "Latest release of Gemini Pro", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "ACCOUNT_RESTRICTED" ], "lifecycle_docs": "Alias", "release_date": null, "knowledge_cutoff": null, "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": true, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": "unknown", "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemini-pro-latest", "version": "Gemini Pro Latest", "displayName": "Gemini Pro Latest", "description": "Latest release of Gemini Pro", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-pro-latest:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-pro-latest:countTokens", "source": "live supportedGenerationMethods" }, { "name": "createCachedContent", "route": "POST /v1beta/cachedContents (model=models/gemini-pro-latest)", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-pro-latest:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-pro-latest:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-pro-latest)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [], "pricing": "billed as the model the alias currently resolves to (see aliases)", "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": { "access": "429 RESOURCE_EXHAUSTED on the Free tier: quota metric generate_content_free_tier_requests / _input_token_count has limit 0 for this model (Pro models are paid-tier only)", "quota_dimensions_model": "gemini-3.1-pro" }, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "live version field holds the display name ('Gemini Pro Latest') instead of a version" ], "last_verified": "2026-09-19", "verification": { "method": "live_api", "verified_at": "2026-09-19T00:00:00Z", "result": "restricted", "http_status": 200, "request_note": "GET /v1beta/models/gemini-pro-latest -> 200; POST :generateContent -> 429 RESOURCE_EXHAUSTED" }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "alias_policy": "hot-swapped with every new release of the variation; 2-week e-mail notice before breaking changes (models.md)", "generate_content_probe": { "http_status": 429, "request": "generateContent 'Reply with OK.' maxOutputTokens=8", "error": { "error": { "code": 429, "message": "You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: https://ai.google.dev/gemini-api/docs/rate-limits. To monitor your current usage, head to: https://ai.dev/rate-limit. \n* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_requests, limit: 0, model: gemini-3.1-pro\n* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_requests, limit: 0, model: gemini-3.1-pro\n* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_input_token_count, limit: 0, model: gemini-3.1-pro\n* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_input_token_count, limit: 0, model: gemini-3.1-pro\nPlease retry in 50.868302469s.", "status": "RESOURCE_EXHAUSTED", "details": [ { "@type": "type.googleapis.com/google.rpc.Help", "links": [ { "description": "Learn more about Gemini API quotas", "url": "https://ai.google.dev/gemini-api/docs/rate-limits" } ] }, { "@type": "type.googleapis.com/google.rpc.QuotaFailure", "violations": [ { "quotaMetric": "generativelanguage.googleapis.com/generate_content_free_tier_requests", "quotaId": "GenerateRequestsPerDayPerProjectPerModel-FreeTier", "quotaDimensions": { "model": "gemini-3.1-pro", "location": "global" } }, { "quotaMetric": "generativelanguage.googleapis.com/generate_content_free_tier_requests", "quotaId": "GenerateRequestsPerMinutePerProjectPerModel-FreeTier", "quotaDimensions": { "location": "global", "model": "gemini-3.1-pro" } }, { "quotaMetric": "generativelanguage.googleapis.com/generate_content_free_tier_input_token_count", "quotaId": "GenerateContentInputTokensPerModelPerMinute-FreeTier", "quotaDimensions": { "location": "global", "model": "gemini-3.1-pro" } }, { "quotaMetric": "generativelanguage.googleapis.com/generate_content_free_tier_input_token_count", "quotaId": "GenerateContentInputTokensPerModelPerDay-FreeTier", "quotaDimensions": { "location": "global", "model": "gemini-3.1-pro" } } ] }, { "@type": "type.googleapis.com/google.rpc.RetryInfo", "retryDelay": "50s" } ] } } }, "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.5-flash-lite", "display_name": "Gemini 2.5 Flash-Lite", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini 2.5", "generation": "2.5", "description": "Stable version of Gemini 2.5 Flash-Lite, released in July of 2025", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "ACCOUNT_RESTRICTED" ], "lifecycle_docs": "Stable (GA)", "release_date": "2025-07-22", "knowledge_cutoff": "January 2025", "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": 1048576, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "thinking": "off", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": true, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "off", "thinking_levels": [ "low", "medium", "high" ], "thinking_level_param": false, "thinking_budget_legacy_param": true, "thought_signatures": false, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": true, "url_context": true, "code_execution": true, "computer_use": false, "file_search": true, "context_caching_explicit": true, "context_caching_docs": true, "context_caching_implicit": true, "batch_api": true, "batch_api_docs": true, "flex_inference": true, "priority_inference": true, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": true, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": [ 10000000, 500000000, 1000000000 ] }, "live_model_metadata": { "name": "models/gemini-2.5-flash-lite", "version": "001", "displayName": "Gemini 2.5 Flash-Lite", "description": "Stable version of Gemini 2.5 Flash-Lite, released in July of 2025", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-2.5-flash-lite:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-2.5-flash-lite:countTokens", "source": "live supportedGenerationMethods" }, { "name": "createCachedContent", "route": "POST /v1beta/cachedContents (model=models/gemini-2.5-flash-lite)", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-2.5-flash-lite:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-2.5-flash-lite:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-2.5-flash-lite)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "google_maps", "category": "server", "support": true }, { "type": "url_context", "category": "server", "support": true }, { "type": "code_execution", "category": "server", "support": true }, { "type": "file_search", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "tiers": { "standard": { "input": 0.1, "audio_input": 0.3, "output": 0.4, "cached_input": 0.01, "cached_audio_input": 0.03, "cache_storage_hour": 1.0 }, "batch": { "input": 0.05, "audio_input": 0.15, "output": 0.2, "cached_input": 0.01, "cached_audio_input": 0.03, "cache_storage_hour": 1.0 }, "flex": { "input": 0.05, "audio_input": 0.15, "output": 0.2, "cached_input": 0.01, "cached_audio_input": 0.03, "cache_storage_hour": 1.0 }, "priority": { "input": 0.18, "audio_input": 0.54, "output": 0.72, "cached_input": 0.018, "cached_audio_input": 0.054, "cache_storage_hour": 1.8 } }, "free_tier": "input/output free of charge; caching not available; Google Search grounding free up to 500 RPD (shared with Flash)", "grounding": { "google_search": "1,500 RPD free (limit shared Flash/Flash-Lite), then $35 per 1,000 grounded prompts; free tier: 500 RPD", "google_maps": "1,500 RPD free, then $25 per 1,000 grounded prompts; free tier 500 RPD" }, "output_includes_thinking_tokens": true, "batch_discount": 0.5, "flex_discount": 0.5, "priority_premium": "1.8x standard (docs: 75-100% more)" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 10000000, "Tier 2": 500000000, "Tier 3": 1000000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": { "access": "This model models/gemini-2.5-flash-lite is no longer available to new users. Please update your code to use models/gemini-3.5-flash-lite for the latest features and improvements. We recommend you to use the Interactions API.", "note": "GET models/{id} still returns 200; only generation is refused for new users" }, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "input/output free of charge; caching not available; Google Search grounding free up to 500 RPD (shared with Flash)", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "live_api", "verified_at": "2026-09-19T00:00:00Z", "result": "restricted", "http_status": 200, "request_note": "GET /v1beta/models/gemini-2.5-flash-lite -> 200; POST :generateContent -> 404 NOT_FOUND" }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-lite", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Stable: `gemini-2.5-flash-lite` - Shut down: `gemini-2.5-flash-lite-preview-09-2025`", "docs_latest_update": "July 2025", "generate_content_probe": { "http_status": 404, "request": "generateContent 'Reply with OK.' maxOutputTokens=8", "error": { "error": { "code": 404, "message": "This model models/gemini-2.5-flash-lite is no longer available to new users. Please update your code to use models/gemini-3.5-flash-lite for the latest features and improvements. We recommend you to use the Interactions API.", "status": "NOT_FOUND" } } }, "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.5-flash-image", "display_name": "Nano Banana", "kind": "stable", "aliases": [], "snapshots": [ "gemini-2.5-flash-image-preview (shut down 2026-01-15)" ], "family": "Gemini 2.5", "generation": "2.5", "description": "Gemini 2.5 Flash Preview Image", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "DEPRECATED" ], "lifecycle_docs": "Deprecated (shutdown scheduled)", "release_date": "2025-10-02", "knowledge_cutoff": "June 2025", "context_window": 32768, "max_output": 32768, "docs_input_token_limit": 65536, "docs_output_token_limit": 32768, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "thinking": "not supported", "capabilities": { "text_input": true, "image_input": true, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": true, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": false, "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": true, "thought_signatures": false, "structured_output": false, "function_calling": false, "parallel_function_calling": false, "compositional_function_calling": false, "google_search_grounding": false, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": true, "flex_inference": false, "priority_inference": false, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": true, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": "unknown", "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": true, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=1", "batch_enqueued_tokens_tier1_tier2_tier3": [ 3000000, 400000000, 1000000000 ] }, "live_model_metadata": { "name": "models/gemini-2.5-flash-image", "version": "2.0", "displayName": "Nano Banana", "description": "Gemini 2.5 Flash Preview Image", "inputTokenLimit": 32768, "outputTokenLimit": 32768, "supportedGenerationMethods": [ "generateContent", "countTokens", "batchGenerateContent" ], "thinking": null, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 1 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-2.5-flash-image:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-2.5-flash-image:countTokens", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-2.5-flash-image:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-2.5-flash-image:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-2.5-flash-image)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [], "pricing": { "currency": "USD", "input": 0.3, "output_per_image": 0.039, "output_image": 30.0, "note": "1290 tokens per image up to 1024x1024", "batch": { "input": 0.15, "output_per_image": 0.0195 }, "flex": "same as batch", "priority": { "input": 0.54, "output_per_image": 0.0702 }, "unit": "per 1M tokens", "free_tier": "not available" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 3000000, "Tier 2": 400000000, "Tier 3": 1000000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-10-02", "earliest_shutdown": "2026-10-02", "replacement": "gemini-3.1-flash-image-preview", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [ "inputTokenLimit live=32768 vs docs=65536", "docs: input limit 65,536 vs live 32,768; live description still says 'Gemini 2.5 Flash Preview Image'" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-image", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Stable: `gemini-2.5-flash-image` - Deprecated: `gemini-2.5-flash-image-preview`", "docs_latest_update": "October 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3-flash-preview", "display_name": "Gemini 3 Flash Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 3", "generation": "3", "description": "Gemini 3 Flash Preview", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW" ], "lifecycle_docs": "Preview", "release_date": "2025-12-17", "knowledge_cutoff": "January 2025 (Gemini 3 model cards; not stated on the API model pages)", "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": 1048576, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "thinking": "high", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": true, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "high", "thinking_levels": [ "minimal", "low", "medium", "high" ], "thinking_level_param": true, "thinking_budget_legacy_param": false, "thought_signatures": true, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": true, "url_context": true, "code_execution": true, "computer_use": true, "file_search": true, "context_caching_explicit": true, "context_caching_docs": true, "context_caching_implicit": true, "batch_api": true, "batch_api_docs": true, "flex_inference": true, "priority_inference": true, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": true, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=2)", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemini-3-flash-preview", "version": "3-flash-preview-12-2025", "displayName": "Gemini 3 Flash Preview", "description": "Gemini 3 Flash Preview", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-3-flash-preview:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-3-flash-preview:countTokens", "source": "live supportedGenerationMethods" }, { "name": "createCachedContent", "route": "POST /v1beta/cachedContents (model=models/gemini-3-flash-preview)", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-3-flash-preview:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-3-flash-preview:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-3-flash-preview)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "google_maps", "category": "server", "support": true }, { "type": "url_context", "category": "server", "support": true }, { "type": "code_execution", "category": "server", "support": true }, { "type": "computer_use", "category": "server", "support": true }, { "type": "file_search", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "tiers": { "standard": { "input": 0.5, "audio_input": 1.0, "output": 3.0, "cached_input": 0.05, "cached_audio_input": 0.1, "cache_storage_hour": 1.0 }, "batch": { "input": 0.25, "audio_input": 0.5, "output": 1.5, "cached_input": 0.05, "cached_audio_input": 0.1, "cache_storage_hour": 1.0 }, "flex": { "input": 0.25, "audio_input": 0.5, "output": 1.5, "cached_input": 0.05, "cached_audio_input": 0.1, "cache_storage_hour": 1.0 }, "priority": { "input": 0.9, "audio_input": 1.8, "output": 5.4, "cached_input": 0.09, "cached_audio_input": 0.18, "cache_storage_hour": 1.8 } }, "free_tier": "input/output/caching free of charge; Batch/Flex not available", "grounding": { "google_search": "5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)", "google_maps": "5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries" }, "output_includes_thinking_tokens": true, "batch_discount": 0.5, "flex_discount": 0.5, "priority_premium": "1.8x standard (docs: 75-100% more)" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "input/output/caching free of charge; Batch/Flex not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3-flash-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - `Preview: gemini-3-flash-preview`", "model_card": "Model card", "docs_latest_update": "December 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3.1-pro-preview", "display_name": "Gemini 3.1 Pro Preview", "kind": "preview", "aliases": [], "snapshots": [ "gemini-3.1-pro-preview-customtools (variant endpoint, same version 3.1-pro-preview-01-2026)" ], "family": "Gemini 3.1", "generation": "3.1", "description": "Gemini 3.1 Pro Preview", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW", "ACCOUNT_RESTRICTED" ], "lifecycle_docs": "Preview", "release_date": "2026-02-19", "knowledge_cutoff": "January 2025 (Gemini 3 model cards; not stated on the API model pages)", "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": 1048576, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "thinking": "high", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": true, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "high", "thinking_levels": [ "low", "medium", "high" ], "thinking_level_param": true, "thinking_budget_legacy_param": false, "thought_signatures": true, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": true, "url_context": true, "code_execution": true, "computer_use": false, "file_search": "Supported (AI Studio only)", "context_caching_explicit": true, "context_caching_docs": true, "context_caching_implicit": true, "batch_api": true, "batch_api_docs": true, "flex_inference": true, "priority_inference": true, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": true, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=2)", "batch_enqueued_tokens_tier1_tier2_tier3": [ 5000000, 500000000, 1000000000 ] }, "live_model_metadata": { "name": "models/gemini-3.1-pro-preview", "version": "3.1-pro-preview-01-2026", "displayName": "Gemini 3.1 Pro Preview", "description": "Gemini 3.1 Pro Preview", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-3.1-pro-preview:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-3.1-pro-preview:countTokens", "source": "live supportedGenerationMethods" }, { "name": "createCachedContent", "route": "POST /v1beta/cachedContents (model=models/gemini-3.1-pro-preview)", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-3.1-pro-preview:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-3.1-pro-preview:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-3.1-pro-preview)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "google_maps", "category": "server", "support": true }, { "type": "url_context", "category": "server", "support": true }, { "type": "code_execution", "category": "server", "support": true }, { "type": "file_search", "category": "server", "support": "Supported (AI Studio only)" }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "tiers": { "standard": { "input": 2.0, "input_over_200k": 4.0, "output": 12.0, "output_over_200k": 18.0, "cached_input": 0.2, "cached_input_over_200k": 0.4, "cache_storage_hour": 4.5 }, "batch": { "input": 1.0, "input_over_200k": 2.0, "output": 6.0, "output_over_200k": 9.0, "cached_input": 0.2, "cached_input_over_200k": 0.4, "cache_storage_hour": 4.5 }, "flex": { "input": 1.0, "input_over_200k": 2.0, "output": 6.0, "output_over_200k": 9.0, "cached_input": 0.2, "cached_input_over_200k": 0.4, "cache_storage_hour": 4.5 }, "priority": { "input": 3.6, "input_over_200k": 7.2, "output": 21.6, "output_over_200k": 32.4, "cached_input": 0.36, "cached_input_over_200k": 0.72, "cache_storage_hour": 8.1 } }, "free_tier": "Not available (paid tier only)", "grounding": { "google_search": "5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)", "google_maps": "5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries" }, "output_includes_thinking_tokens": true, "batch_discount": 0.5, "flex_discount": 0.5, "priority_premium": "1.8x standard (docs: 75-100% more)", "long_context_threshold": 200000 }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 5000000, "Tier 2": 500000000, "Tier 3": 1000000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": { "access": "429 RESOURCE_EXHAUSTED on the Free tier: quota metric generate_content_free_tier_requests / _input_token_count has limit 0 for this model (Pro models are paid-tier only)", "quota_dimensions_model": "gemini-3.1-pro" }, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "Not available (paid tier only)", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "live_api", "verified_at": "2026-09-19T00:00:00Z", "result": "restricted", "http_status": null, "request_note": "POST :generateContent -> 429 RESOURCE_EXHAUSTED" }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Preview: `gemini-3.1-pro-preview` - Preview: `gemini-3.1-pro-preview-customtools` \\*", "model_card": "Model card", "docs_latest_update": "February 2026", "generate_content_probe": { "http_status": 429, "request": "generateContent 'Reply with OK.' maxOutputTokens=8", "error": { "error": { "code": 429, "message": "You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: https://ai.google.dev/gemini-api/docs/rate-limits. To monitor your current usage, head to: https://ai.dev/rate-limit. \n* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_input_token_count, limit: 0, model: gemini-3.1-pro\n* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_input_token_count, limit: 0, model: gemini-3.1-pro\n* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_requests, limit: 0, model: gemini-3.1-pro\n* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_requests, limit: 0, model: gemini-3.1-pro\nPlease retry in 54.22098241s.", "status": "RESOURCE_EXHAUSTED", "details": [ { "@type": "type.googleapis.com/google.rpc.Help", "links": [ { "description": "Learn more about Gemini API quotas", "url": "https://ai.google.dev/gemini-api/docs/rate-limits" } ] }, { "@type": "type.googleapis.com/google.rpc.QuotaFailure", "violations": [ { "quotaMetric": "generativelanguage.googleapis.com/generate_content_free_tier_input_token_count", "quotaId": "GenerateContentInputTokensPerModelPerDay-FreeTier", "quotaDimensions": { "location": "global", "model": "gemini-3.1-pro" } }, { "quotaMetric": "generativelanguage.googleapis.com/generate_content_free_tier_input_token_count", "quotaId": "GenerateContentInputTokensPerModelPerMinute-FreeTier", "quotaDimensions": { "model": "gemini-3.1-pro", "location": "global" } }, { "quotaMetric": "generativelanguage.googleapis.com/generate_content_free_tier_requests", "quotaId": "GenerateRequestsPerMinutePerProjectPerModel-FreeTier", "quotaDimensions": { "location": "global", "model": "gemini-3.1-pro" } }, { "quotaMetric": "generativelanguage.googleapis.com/generate_content_free_tier_requests", "quotaId": "GenerateRequestsPerDayPerProjectPerModel-FreeTier", "quotaDimensions": { "model": "gemini-3.1-pro", "location": "global" } } ] }, { "@type": "type.googleapis.com/google.rpc.RetryInfo", "retryDelay": "54s" } ] } } }, "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3.1-pro-preview-customtools", "display_name": "Gemini 3.1 Pro Preview Custom Tools", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 3.1", "generation": "3.1", "description": "Gemini 3.1 Pro Preview optimized for custom tool usage", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW" ], "lifecycle_docs": "Preview", "release_date": "2026-02-19", "knowledge_cutoff": "January 2025 (Gemini 3 model cards; not stated on the API model pages)", "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": 1048576, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "thinking": "high", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": true, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "high", "thinking_levels": [ "low", "medium", "high" ], "thinking_level_param": true, "thinking_budget_legacy_param": false, "thought_signatures": true, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": true, "url_context": true, "code_execution": true, "computer_use": false, "file_search": "Supported (AI Studio only)", "context_caching_explicit": true, "context_caching_docs": true, "context_caching_implicit": true, "batch_api": true, "batch_api_docs": true, "flex_inference": true, "priority_inference": true, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": "unknown", "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=2)", "batch_enqueued_tokens_tier1_tier2_tier3": [ 5000000, 500000000, 1000000000 ] }, "live_model_metadata": { "name": "models/gemini-3.1-pro-preview-customtools", "version": "3.1-pro-preview-01-2026", "displayName": "Gemini 3.1 Pro Preview Custom Tools", "description": "Gemini 3.1 Pro Preview optimized for custom tool usage", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-3.1-pro-preview-customtools:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-3.1-pro-preview-customtools:countTokens", "source": "live supportedGenerationMethods" }, { "name": "createCachedContent", "route": "POST /v1beta/cachedContents (model=models/gemini-3.1-pro-preview-customtools)", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-3.1-pro-preview-customtools:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-3.1-pro-preview-customtools:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-3.1-pro-preview-customtools)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "google_maps", "category": "server", "support": true }, { "type": "url_context", "category": "server", "support": true }, { "type": "code_execution", "category": "server", "support": true }, { "type": "file_search", "category": "server", "support": "Supported (AI Studio only)" }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "tiers": { "standard": { "input": 2.0, "input_over_200k": 4.0, "output": 12.0, "output_over_200k": 18.0, "cached_input": 0.2, "cached_input_over_200k": 0.4, "cache_storage_hour": 4.5 }, "batch": { "input": 1.0, "input_over_200k": 2.0, "output": 6.0, "output_over_200k": 9.0, "cached_input": 0.2, "cached_input_over_200k": 0.4, "cache_storage_hour": 4.5 }, "flex": { "input": 1.0, "input_over_200k": 2.0, "output": 6.0, "output_over_200k": 9.0, "cached_input": 0.2, "cached_input_over_200k": 0.4, "cache_storage_hour": 4.5 }, "priority": { "input": 3.6, "input_over_200k": 7.2, "output": 21.6, "output_over_200k": 32.4, "cached_input": 0.36, "cached_input_over_200k": 0.72, "cache_storage_hour": 8.1 } }, "free_tier": "Not available (paid tier only)", "grounding": { "google_search": "5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)", "google_maps": "5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries" }, "output_includes_thinking_tokens": true, "batch_discount": 0.5, "flex_discount": 0.5, "priority_premium": "1.8x standard (docs: 75-100% more)", "long_context_threshold": 200000, "same_as": "gemini-3.1-pro-preview (pricing.md: 'Custom Tools endpoint ... Same as Gemini 3.1 Pro Preview pricing')" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 5000000, "Tier 2": 500000000, "Tier 3": 1000000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "Not available (paid tier only)", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "live-listed id without a dedicated docs model page" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Preview: `gemini-3.1-pro-preview` - Preview: `gemini-3.1-pro-preview-customtools` \\*", "model_card": "Model card", "docs_latest_update": "February 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3.1-flash-lite-preview", "display_name": "Gemini 3.1 Flash Lite Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 3.1", "generation": "3.1", "description": "Gemini 3.1 Flash Lite Preview", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2026-03-03", "knowledge_cutoff": "January 2025 (Gemini 3 model cards; not stated on the API model pages)", "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": 1048576, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": true, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": true, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": true, "url_context": true, "code_execution": true, "computer_use": false, "file_search": true, "context_caching_explicit": true, "context_caching_docs": true, "context_caching_implicit": true, "batch_api": true, "batch_api_docs": true, "flex_inference": true, "priority_inference": true, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": true, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=2)", "batch_enqueued_tokens_tier1_tier2_tier3": [ 10000000, 500000000, 1000000000 ] }, "live_model_metadata": { "name": "models/gemini-3.1-flash-lite-preview", "version": "3.1-flash-lite-preview-03-2026", "displayName": "Gemini 3.1 Flash Lite Preview", "description": "Gemini 3.1 Flash Lite Preview", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-3.1-flash-lite-preview:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-3.1-flash-lite-preview:countTokens", "source": "live supportedGenerationMethods" }, { "name": "createCachedContent", "route": "POST /v1beta/cachedContents (model=models/gemini-3.1-flash-lite-preview)", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-3.1-flash-lite-preview:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-3.1-flash-lite-preview:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-3.1-flash-lite-preview)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "google_maps", "category": "server", "support": true }, { "type": "url_context", "category": "server", "support": true }, { "type": "code_execution", "category": "server", "support": true }, { "type": "file_search", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": "not listed on pricing.md", "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 10000000, "Tier 2": 500000000, "Tier 3": 1000000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2026-03-03", "earliest_shutdown": "2026-05-25", "replacement": "gemini-3.1-flash-lite", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - *Shut down* : `gemini-3.1-flash-lite-preview`", "model_card": "Model card", "docs_latest_update": "March 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3.1-flash-lite", "display_name": "Gemini 3.1 Flash Lite", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini 3.1", "generation": "3.1", "description": "Gemini 3.1 Flash Lite", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "DEPRECATED" ], "lifecycle_docs": "Deprecated (shutdown scheduled)", "release_date": "2026-05-07", "knowledge_cutoff": "January 2025 (Gemini 3 model cards; not stated on the API model pages)", "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": 1048576, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "thinking": "unknown (docs table omits it; openai.md maps minimal/low/medium/high)", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": true, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown (docs table omits it; openai.md maps minimal/low/medium/high)", "thinking_levels": [ "minimal", "low", "medium", "high" ], "thinking_level_param": true, "thinking_budget_legacy_param": false, "thought_signatures": true, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": true, "url_context": true, "code_execution": true, "computer_use": false, "file_search": true, "context_caching_explicit": true, "context_caching_docs": true, "context_caching_implicit": true, "batch_api": true, "batch_api_docs": true, "flex_inference": true, "priority_inference": true, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": true, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=2)", "batch_enqueued_tokens_tier1_tier2_tier3": [ 10000000, 500000000, 1000000000 ] }, "live_model_metadata": { "name": "models/gemini-3.1-flash-lite", "version": "3.1-flash-lite-05-2026", "displayName": "Gemini 3.1 Flash Lite", "description": "Gemini 3.1 Flash Lite", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-3.1-flash-lite:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-3.1-flash-lite:countTokens", "source": "live supportedGenerationMethods" }, { "name": "createCachedContent", "route": "POST /v1beta/cachedContents (model=models/gemini-3.1-flash-lite)", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-3.1-flash-lite:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-3.1-flash-lite:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-3.1-flash-lite)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "google_maps", "category": "server", "support": true }, { "type": "url_context", "category": "server", "support": true }, { "type": "code_execution", "category": "server", "support": true }, { "type": "file_search", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "tiers": { "standard": { "input": 0.25, "audio_input": 0.5, "output": 1.5, "cached_input": 0.025, "cached_audio_input": 0.05, "cache_storage_hour": 1.0 }, "batch": { "input": 0.125, "audio_input": 0.25, "output": 0.75, "cached_input": 0.0125, "cached_audio_input": 0.025, "cache_storage_hour": 0.5 }, "flex": { "input": 0.125, "audio_input": 0.25, "output": 0.75, "cached_input": 0.0125, "cached_audio_input": 0.025, "cache_storage_hour": 0.5 }, "priority": { "input": 0.45, "audio_input": 0.9, "output": 2.7, "cached_input": 0.045, "cached_audio_input": 0.09, "cache_storage_hour": 1.8 } }, "free_tier": "input/output free of charge; caching not available on free tier", "grounding": { "google_search": "5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)", "google_maps": "5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries" }, "output_includes_thinking_tokens": true, "batch_discount": 0.5, "flex_discount": 0.5, "priority_premium": "1.8x standard (docs: 75-100% more)" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 10000000, "Tier 2": 500000000, "Tier 3": 1000000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "input/output free of charge; caching not available on free tier", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2026-05-07", "earliest_shutdown": "2027-05-07", "replacement": "gemini-3.5-flash-lite", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - `Stable: gemini-3.1-flash-lite`", "model_card": "Model card", "docs_latest_update": "May 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3-pro-image-preview", "display_name": "Nano Banana Pro", "kind": "preview", "aliases": [ "nano-banana-pro-preview (same live metadata: version 3.0, Nano Banana Pro)" ], "snapshots": [], "family": "Gemini 3", "generation": "3", "description": "Gemini 3 Pro Image Preview", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-11-20", "knowledge_cutoff": "January 2025", "context_window": 131072, "max_output": 32768, "docs_input_token_limit": 65536, "docs_output_token_limit": 32768, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": true, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": true, "structured_output": true, "function_calling": false, "parallel_function_calling": false, "compositional_function_calling": false, "google_search_grounding": true, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": true, "flex_inference": true, "priority_inference": true, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": true, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": "unknown", "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": true, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=1)", "batch_enqueued_tokens_tier1_tier2_tier3": [ 2000000, 270000000, 1000000000 ] }, "live_model_metadata": { "name": "models/gemini-3-pro-image-preview", "version": "3.0", "displayName": "Nano Banana Pro", "description": "Gemini 3 Pro Image Preview", "inputTokenLimit": 131072, "outputTokenLimit": 32768, "supportedGenerationMethods": [ "generateContent", "countTokens", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 1 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-3-pro-image-preview:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-3-pro-image-preview:countTokens", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-3-pro-image-preview:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-3-pro-image-preview:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-3-pro-image-preview)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [ { "type": "google_search", "category": "server", "support": true } ], "pricing": { "currency": "USD", "input": 2.0, "input_per_image": 0.0011, "output_text": 12.0, "output_image": 120.0, "per_image": { "1K/2K (1120 tok)": 0.134, "4K (2000 tok)": 0.24 }, "batch": { "input_text": 1.0, "input_per_image": 0.0006, "output_text": 6.0, "per_image_1k_2k": 0.067, "per_image_4k": 0.12 }, "flex": "same as batch", "priority": { "input": 3.6, "output_text": 21.6, "output_image": 216.0 }, "unit": "per 1M tokens", "free_tier": "not available", "grounding": "gemini3 (Google Search)", "same_as": "gemini-3-pro-image" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 2000000, "Tier 2": 270000000, "Tier 3": 1000000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-11-20", "earliest_shutdown": "2026-06-25", "replacement": "gemini-3-pro-image", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [ "inputTokenLimit live=131072 vs docs=65536" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3-pro-image-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - `Preview: gemini-3-pro-image-preview`", "docs_latest_update": "November 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3-pro-image", "display_name": "Nano Banana Pro", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini 3", "generation": "3", "description": "Gemini 3 Pro Image", "status": [ "DOCUMENTED", "LIVE_DISCOVERED" ], "lifecycle_docs": "Stable (GA)", "release_date": "2026-05-28", "knowledge_cutoff": null, "context_window": 131072, "max_output": 32768, "docs_input_token_limit": 65536, "docs_output_token_limit": 32768, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": true, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": true, "structured_output": false, "function_calling": false, "parallel_function_calling": false, "compositional_function_calling": false, "google_search_grounding": true, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": true, "flex_inference": false, "priority_inference": false, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": true, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=1)", "batch_enqueued_tokens_tier1_tier2_tier3": [ 2000000, 270000000, 1000000000 ] }, "live_model_metadata": { "name": "models/gemini-3-pro-image", "version": "3.0", "displayName": "Nano Banana Pro", "description": "Gemini 3 Pro Image", "inputTokenLimit": 131072, "outputTokenLimit": 32768, "supportedGenerationMethods": [ "generateContent", "countTokens", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 1 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-3-pro-image:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-3-pro-image:countTokens", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-3-pro-image:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-3-pro-image:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-3-pro-image)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [ { "type": "google_search", "category": "server", "support": true } ], "pricing": { "currency": "USD", "input": 2.0, "input_per_image": 0.0011, "output_text": 12.0, "output_image": 120.0, "per_image": { "1K/2K (1120 tok)": 0.134, "4K (2000 tok)": 0.24 }, "batch": { "input_text": 1.0, "input_per_image": 0.0006, "output_text": 6.0, "per_image_1k_2k": 0.067, "per_image_4k": 0.12 }, "flex": "same as batch", "priority": { "input": 3.6, "output_text": 21.6, "output_image": 216.0 }, "unit": "per 1M tokens", "free_tier": "not available", "grounding": "gemini3 (Google Search)" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 2000000, "Tier 2": 270000000, "Tier 3": 1000000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "inputTokenLimit live=131072 vs docs=65536" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3-pro-image", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Stable: `gemini-3-pro-image`", "model_card": "Model card", "docs_latest_update": "November 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "nano-banana-pro-preview", "display_name": "Nano Banana Pro", "kind": "preview", "aliases": [ "gemini-3-pro-image-preview" ], "snapshots": [], "family": "Gemini 3 (image)", "generation": "3", "description": "Gemini 3 Pro Image Preview", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-11-20", "knowledge_cutoff": "January 2025", "context_window": 131072, "max_output": 32768, "docs_input_token_limit": 65536, "docs_output_token_limit": 32768, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": true, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": true, "function_calling": false, "parallel_function_calling": false, "compositional_function_calling": false, "google_search_grounding": true, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": true, "flex_inference": true, "priority_inference": true, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": true, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": "unknown", "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": true, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=1", "batch_enqueued_tokens_tier1_tier2_tier3": [ 2000000, 270000000, 1000000000 ] }, "live_model_metadata": { "name": "models/nano-banana-pro-preview", "version": "3.0", "displayName": "Nano Banana Pro", "description": "Gemini 3 Pro Image Preview", "inputTokenLimit": 131072, "outputTokenLimit": 32768, "supportedGenerationMethods": [ "generateContent", "countTokens", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 1 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/nano-banana-pro-preview:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/nano-banana-pro-preview:countTokens", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/nano-banana-pro-preview:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/nano-banana-pro-preview:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=nano-banana-pro-preview)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [ { "type": "google_search", "category": "server", "support": true } ], "pricing": { "currency": "USD", "input": 2.0, "input_per_image": 0.0011, "output_text": 12.0, "output_image": 120.0, "per_image": { "1K/2K (1120 tok)": 0.134, "4K (2000 tok)": 0.24 }, "batch": { "input_text": 1.0, "input_per_image": 0.0006, "output_text": 6.0, "per_image_1k_2k": 0.067, "per_image_4k": 0.12 }, "flex": "same as batch", "priority": { "input": 3.6, "output_text": 21.6, "output_image": 216.0 }, "unit": "per 1M tokens", "free_tier": "not available", "grounding": "gemini3 (Google Search)", "same_as": "gemini-3-pro-image" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 2000000, "Tier 2": 270000000, "Tier 3": 1000000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-11-20", "earliest_shutdown": "2026-06-25", "replacement": "gemini-3-pro-image", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [ "inputTokenLimit live=131072 vs docs=65536", "live-listed id without a dedicated docs model page" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3-pro-image-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - `Preview: gemini-3-pro-image-preview`", "docs_latest_update": "November 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3.1-flash-image-preview", "display_name": "Nano Banana 2", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 3.1", "generation": "3.1", "description": "Gemini 3.1 Flash Image Preview.", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2026-02-26", "knowledge_cutoff": "January 2025", "context_window": 65536, "max_output": 65536, "docs_input_token_limit": 131072, "docs_output_token_limit": 32768, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text", "image" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": false, "video_input": false, "pdf_input": true, "text_output": true, "image_output": true, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": true, "structured_output": false, "function_calling": false, "parallel_function_calling": false, "compositional_function_calling": false, "google_search_grounding": true, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": true, "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": true, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": "unknown", "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=1)", "batch_enqueued_tokens_tier1_tier2_tier3": [ 1000000, 250000000, 750000000 ] }, "live_model_metadata": { "name": "models/gemini-3.1-flash-image-preview", "version": "3.0", "displayName": "Nano Banana 2", "description": "Gemini 3.1 Flash Image Preview.", "inputTokenLimit": 65536, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 1 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-3.1-flash-image-preview:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-3.1-flash-image-preview:countTokens", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-3.1-flash-image-preview:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-3.1-flash-image-preview:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-3.1-flash-image-preview)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [ { "type": "google_search", "category": "server", "support": true } ], "pricing": { "currency": "USD", "input": 0.5, "output_text": 3.0, "output_image": 60.0, "per_image": { "0.5K (747 tok)": 0.045, "1K (1120 tok)": 0.067, "2K (1680 tok)": 0.101, "4K (2520 tok)": 0.151 }, "batch": { "input": 0.25, "output_text": 1.5, "output_image": 30.0 }, "unit": "per 1M tokens", "free_tier": "not available", "grounding": "5,000 free search requests/month shared, then $14/1k (web + image search grounding)", "same_as": "gemini-3.1-flash-image" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 1000000, "Tier 2": 250000000, "Tier 3": 750000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2026-02-26", "earliest_shutdown": "2026-06-25", "replacement": "gemini-3.1-flash-image", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [ "inputTokenLimit live=65536 vs docs=131072", "outputTokenLimit live=65536 vs docs=32768" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-image-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - `Preview: gemini-3.1-flash-image-preview`", "docs_latest_update": "February 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3.1-flash-image", "display_name": "Nano Banana 2", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini 3.1", "generation": "3.1", "description": "Gemini 3.1 Flash Image.", "status": [ "DOCUMENTED", "LIVE_DISCOVERED" ], "lifecycle_docs": "Stable (GA)", "release_date": "2026-05-28", "knowledge_cutoff": null, "context_window": 65536, "max_output": 65536, "docs_input_token_limit": 131072, "docs_output_token_limit": 32768, "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text", "image" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": false, "video_input": true, "pdf_input": true, "text_output": true, "image_output": true, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": true, "structured_output": false, "function_calling": false, "parallel_function_calling": false, "compositional_function_calling": false, "google_search_grounding": true, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": true, "flex_inference": false, "priority_inference": false, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": true, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=1)", "batch_enqueued_tokens_tier1_tier2_tier3": [ 1000000, 250000000, 750000000 ] }, "live_model_metadata": { "name": "models/gemini-3.1-flash-image", "version": "3.0", "displayName": "Nano Banana 2", "description": "Gemini 3.1 Flash Image.", "inputTokenLimit": 65536, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 1 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-3.1-flash-image:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-3.1-flash-image:countTokens", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-3.1-flash-image:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-3.1-flash-image:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-3.1-flash-image)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [ { "type": "google_search", "category": "server", "support": true } ], "pricing": { "currency": "USD", "input": 0.5, "output_text": 3.0, "output_image": 60.0, "per_image": { "0.5K (747 tok)": 0.045, "1K (1120 tok)": 0.067, "2K (1680 tok)": 0.101, "4K (2520 tok)": 0.151 }, "batch": { "input": 0.25, "output_text": 1.5, "output_image": 30.0 }, "unit": "per 1M tokens", "free_tier": "not available", "grounding": "5,000 free search requests/month shared, then $14/1k (web + image search grounding)" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 1000000, "Tier 2": 250000000, "Tier 3": 750000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "inputTokenLimit live=65536 vs docs=131072", "outputTokenLimit live=65536 vs docs=32768" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-image", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Stable: `gemini-3.1-flash-image`", "model_card": "Model card", "docs_latest_update": "February 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3.1-flash-lite-image", "display_name": "Nano Banana 2 Lite", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini 3.1", "generation": "3.1", "description": "Gemini 3.1 Flash Lite Image.", "status": [ "DOCUMENTED", "LIVE_DISCOVERED" ], "lifecycle_docs": "Stable (GA)", "release_date": "2026-06-30", "knowledge_cutoff": null, "context_window": 65536, "max_output": 65536, "docs_input_token_limit": 65536, "docs_output_token_limit": 4096, "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text", "image" ] }, "thinking": "minimal", "capabilities": { "text_input": true, "image_input": true, "audio_input": false, "video_input": true, "pdf_input": true, "text_output": true, "image_output": true, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "Supported (minimal and high)", "thinking_live_flag": true, "thinking_default_level": "minimal", "thinking_levels": [ "minimal", "high" ], "thinking_level_param": true, "thinking_budget_legacy_param": false, "thought_signatures": true, "structured_output": false, "function_calling": false, "parallel_function_calling": false, "compositional_function_calling": false, "google_search_grounding": false, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": true, "flex_inference": false, "priority_inference": false, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": true, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=1)", "batch_enqueued_tokens_tier1_tier2_tier3": [ 2000000, 270000000, 1000000000 ] }, "live_model_metadata": { "name": "models/gemini-3.1-flash-lite-image", "version": "3.0", "displayName": "Nano Banana 2 Lite", "description": "Gemini 3.1 Flash Lite Image.", "inputTokenLimit": 65536, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 1 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-3.1-flash-lite-image:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-3.1-flash-lite-image:countTokens", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-3.1-flash-lite-image:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-3.1-flash-lite-image:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-3.1-flash-lite-image)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [], "pricing": { "currency": "USD", "input": 0.25, "output_text": 1.5, "output_image": 30.0, "per_image": { "1K (1120 tok)": 0.0336 }, "batch": { "input": 0.125, "output_text": 0.75, "output_image": 15.0 }, "unit": "per 1M tokens", "free_tier": "not available" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 2000000, "Tier 2": 270000000, "Tier 3": 1000000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "outputTokenLimit live=65536 vs docs=4096" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite-image", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Stable: `gemini-3.1-flash-lite-image`", "model_card": "Model card", "docs_latest_update": "June 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3.5-flash", "display_name": "Gemini 3.5 Flash", "kind": "stable", "aliases": [ "gemini-flash-latest pointed here 2026-05-19 -> 2026-09 (now gemini-3.8-flash)" ], "snapshots": [], "family": "Gemini 3.5", "generation": "3.5", "description": "Gemini 3.5 Flash", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "LIVE_VERIFIED" ], "lifecycle_docs": "Stable (GA)", "release_date": "2026-05-19", "knowledge_cutoff": "January 2025 (Gemini 3 model cards; not stated on the API model pages)", "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": 1048576, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "thinking": "medium", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": true, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "medium", "thinking_levels": [ "minimal", "low", "medium", "high" ], "thinking_level_param": true, "thinking_budget_legacy_param": false, "thought_signatures": true, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": true, "url_context": true, "code_execution": true, "computer_use": "Supported (Preview)", "file_search": true, "context_caching_explicit": true, "context_caching_docs": true, "context_caching_implicit": true, "batch_api": true, "batch_api_docs": true, "flex_inference": true, "priority_inference": true, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": true, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=2)", "batch_enqueued_tokens_tier1_tier2_tier3": [ 3000000, 400000000, 1000000000 ] }, "live_model_metadata": { "name": "models/gemini-3.5-flash", "version": "3.5-flash-05-2026", "displayName": "Gemini 3.5 Flash", "description": "Gemini 3.5 Flash", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-3.5-flash:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-3.5-flash:countTokens", "source": "live supportedGenerationMethods" }, { "name": "createCachedContent", "route": "POST /v1beta/cachedContents (model=models/gemini-3.5-flash)", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-3.5-flash:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-3.5-flash:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-3.5-flash)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "google_maps", "category": "server", "support": true }, { "type": "url_context", "category": "server", "support": true }, { "type": "code_execution", "category": "server", "support": true }, { "type": "computer_use", "category": "server", "support": "Supported (Preview)" }, { "type": "file_search", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "tiers": { "standard": { "input": 1.5, "output": 9.0, "cached_input": 0.15, "cache_storage_hour": 1.0 }, "batch": { "input": 0.75, "output": 4.5, "cached_input": 0.075, "cache_storage_hour": 1.0 }, "flex": { "input": 0.75, "output": 4.5, "cached_input": 0.08, "cache_storage_hour": 1.0 }, "priority": { "input": 2.7, "output": 16.2, "cached_input": 0.27, "cache_storage_hour": 1.0 } }, "free_tier": "input/output/caching free of charge; Batch/Flex not available", "grounding": { "google_search": "5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)", "google_maps": "5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries" }, "output_includes_thinking_tokens": true, "batch_discount": 0.5, "flex_discount": 0.5, "priority_premium": "1.8x standard (docs: 75-100% more)" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 3000000, "Tier 2": 400000000, "Tier 3": 1000000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "input/output/caching free of charge; Batch/Flex not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "live_api", "verified_at": "2026-09-19T00:00:00Z", "result": "success", "http_status": null, "request_note": "POST :generateContent -> 200 (modelVersion=gemini-3.5-flash)" }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Stable: `gemini-3.5-flash` - Preview: `gemini-3-flash-preview`", "model_card": "Model card", "docs_latest_update": "May 2026", "generate_content_probe": { "http_status": 200, "request": "generateContent 'Reply with OK.' maxOutputTokens=8", "modelVersion": "gemini-3.5-flash", "responseId_present": true, "finishReason": "MAX_TOKENS", "usageMetadata": { "promptTokenCount": 5, "totalTokenCount": 10, "promptTokensDetails": [ { "modality": "TEXT", "tokenCount": 5 } ], "thoughtsTokenCount": 5, "serviceTier": "standard" }, "thoughtSignature_present": false, "text": "", "response_headers": { "Server-Timing": "gfet4t7; dur=5171" }, "header_names": [ "Accept-Ranges", "Alt-Svc", "Connection", "Content-Type", "Date", "Server", "Server-Timing", "Transfer-Encoding", "Vary", "X-Content-Type-Options", "X-Frame-Options", "X-Gemini-Service-Tier", "X-XSS-Protection" ] }, "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3.5-flash-lite", "display_name": "Gemini 3.5 Flash Lite", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini 3.5", "generation": "3.5", "description": "Gemini 3.5 Flash Lite", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "LIVE_VERIFIED" ], "lifecycle_docs": "Stable (GA)", "release_date": "2026-07-21", "knowledge_cutoff": "January 2025 (Gemini 3 model cards; not stated on the API model pages)", "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": 1048576, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "thinking": "minimal", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": true, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "minimal", "thinking_levels": [ "minimal", "low", "medium", "high" ], "thinking_level_param": true, "thinking_budget_legacy_param": false, "thought_signatures": true, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": true, "url_context": true, "code_execution": true, "computer_use": "Supported (Preview)", "file_search": true, "context_caching_explicit": true, "context_caching_docs": true, "context_caching_implicit": true, "batch_api": true, "batch_api_docs": true, "flex_inference": true, "priority_inference": true, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=2)", "batch_enqueued_tokens_tier1_tier2_tier3": [ 10000000, 500000000, 1000000000 ] }, "live_model_metadata": { "name": "models/gemini-3.5-flash-lite", "version": "3.5-flash-lite-07-2026", "displayName": "Gemini 3.5 Flash Lite", "description": "Gemini 3.5 Flash Lite", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-3.5-flash-lite:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-3.5-flash-lite:countTokens", "source": "live supportedGenerationMethods" }, { "name": "createCachedContent", "route": "POST /v1beta/cachedContents (model=models/gemini-3.5-flash-lite)", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-3.5-flash-lite:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-3.5-flash-lite:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-3.5-flash-lite)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "google_maps", "category": "server", "support": true }, { "type": "url_context", "category": "server", "support": true }, { "type": "code_execution", "category": "server", "support": true }, { "type": "computer_use", "category": "server", "support": "Supported (Preview)" }, { "type": "file_search", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "tiers": { "standard": { "input": 0.3, "output": 2.5, "cached_input": 0.03, "cache_storage_hour": 1.0 }, "batch": { "input": 0.15, "output": 1.25, "cached_input": 0.02, "cache_storage_hour": 1.0 }, "flex": { "input": 0.15, "output": 1.25, "cached_input": 0.02, "cache_storage_hour": 1.0 }, "priority": { "input": 0.54, "output": 4.5, "cached_input": 0.05, "cache_storage_hour": 1.0 } }, "free_tier": "input/output free of charge on all four rows (page lists Batch/Flex as 'Free of charge' too); caching not available on free tier", "grounding": { "google_search": "5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)", "google_maps": "5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries" }, "output_includes_thinking_tokens": true, "batch_discount": 0.5, "flex_discount": 0.5, "priority_premium": "1.8x standard (docs: 75-100% more)", "input_note": "text / image / video / audio same price" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 10000000, "Tier 2": 500000000, "Tier 3": 1000000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "input/output free of charge on all four rows (page lists Batch/Flex as 'Free of charge' too); caching not available on free tier", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "live_api", "verified_at": "2026-09-19T00:00:00Z", "result": "success", "http_status": 200, "request_note": "GET /v1beta/models/gemini-3.5-flash-lite -> 200; POST :generateContent -> 200 (modelVersion=gemini-3.5-flash-lite)" }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash-lite", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Stable: `gemini-3.5-flash-lite`", "model_card": "Model card", "docs_latest_update": "July 2026", "generate_content_probe": { "http_status": 200, "request": "generateContent 'Reply with OK.' maxOutputTokens=8", "modelVersion": "gemini-3.5-flash-lite", "responseId_present": true, "finishReason": "STOP", "usageMetadata": { "promptTokenCount": 5, "candidatesTokenCount": 2, "totalTokenCount": 7, "promptTokensDetails": [ { "modality": "TEXT", "tokenCount": 5 } ], "serviceTier": "standard" }, "thoughtSignature_present": true, "text": "OK.", "response_headers": { "Server-Timing": "gfet4t7; dur=2714" }, "header_names": [ "Accept-Ranges", "Alt-Svc", "Connection", "Content-Type", "Date", "Server", "Server-Timing", "Transfer-Encoding", "Vary", "X-Content-Type-Options", "X-Frame-Options", "X-Gemini-Service-Tier", "X-XSS-Protection" ] }, "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-omni-flash-preview", "display_name": "Gemini Omni Flash Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini Omni", "generation": "preview", "description": "Gemini Omni Flash Preview", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW", "DEPRECATED" ], "lifecycle_docs": "Deprecated (shutdown scheduled)", "release_date": "2026-06-30", "knowledge_cutoff": null, "context_window": 131072, "max_output": 65536, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "video" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": false, "video_input": true, "pdf_input": false, "text_output": false, "image_output": false, "audio_output": false, "video_output": true, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": false, "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": true, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemini-omni-flash-preview", "version": "001", "displayName": "Gemini Omni Flash Preview", "description": "Gemini Omni Flash Preview", "inputTokenLimit": 131072, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-omni-flash-preview:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-omni-flash-preview:countTokens", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-omni-flash-preview:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-omni-flash-preview)", "source": "docs (music-generation.md / omni.md use the Interactions API)" } ], "tools": [], "pricing": { "currency": "USD", "input": 1.5, "output_text": 9.0, "output_video": 17.5, "unit": "per 1M tokens", "note": "5,792 tokens per second of 720p video => ~$0.10 per second", "free_tier": "not available", "same_as": "gemini-omni-1.1-flash" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2026-06-30", "earliest_shutdown": "2026-09-30", "replacement": "gemini-omni-1.1-flash", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-omni-flash", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Model versions: - Stable: `gemini-omni-1.1-flash` - Preview: `gemini-omni-flash-preview`", "docs_latest_update": "August 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-omni-1.1-flash", "display_name": "Gemini Omni 1.1 Flash", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini Omni", "generation": "1.1", "description": "Gemini Omni 1.1 Flash ", "status": [ "DOCUMENTED", "LIVE_DISCOVERED" ], "lifecycle_docs": "Stable (GA)", "release_date": "2026-08-27", "knowledge_cutoff": null, "context_window": 131072, "max_output": 65536, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "video" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": false, "video_input": true, "pdf_input": false, "text_output": false, "image_output": false, "audio_output": false, "video_output": true, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": false, "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": true, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemini-omni-1.1-flash", "version": "001", "displayName": "Gemini Omni 1.1 Flash", "description": "Gemini Omni 1.1 Flash ", "inputTokenLimit": 131072, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-omni-1.1-flash:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-omni-1.1-flash:countTokens", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-omni-1.1-flash:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-omni-1.1-flash)", "source": "docs (music-generation.md / omni.md use the Interactions API)" } ], "tools": [], "pricing": { "currency": "USD", "input": 1.5, "output_text": 9.0, "output_video": 17.5, "unit": "per 1M tokens", "note": "5,792 tokens per second of 720p video => ~$0.10 per second", "free_tier": "not available" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-omni-flash", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Model versions: - Stable: `gemini-omni-1.1-flash` - Preview: `gemini-omni-flash-preview`", "docs_latest_update": "August 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3.5-transcribe", "display_name": "Gemini 3.5 Transcribe", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini 3.5", "generation": "3.5", "description": "Gemini 3.5 Transcribe", "status": [ "DOCUMENTED", "LIVE_DISCOVERED" ], "lifecycle_docs": "Stable (GA)", "release_date": "2026-08", "knowledge_cutoff": "January 2025 (Gemini 3 model cards; not stated on the API model pages)", "context_window": 98304, "max_output": 32768, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "thinking": "not supported", "capabilities": { "text_input": false, "image_input": false, "audio_input": true, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": false, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": false, "parallel_function_calling": false, "compositional_function_calling": false, "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": false, "flex_inference": false, "priority_inference": false, "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": true, "live_translation": false, "speaker_diarization": true, "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": "unknown", "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=2)", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemini-3.5-transcribe", "version": "3.5-transcribe-08-2026", "displayName": "Gemini 3.5 Transcribe", "description": "Gemini 3.5 Transcribe", "inputTokenLimit": 98304, "outputTokenLimit": 32768, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-3.5-transcribe:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-3.5-transcribe:countTokens", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-3.5-transcribe:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-3.5-transcribe)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [], "pricing": { "currency": "USD", "input_audio": 2.0, "input_audio_per_min": 0.003, "output_text": 12.0, "output_text_per_min": 0.002, "unit": "per 1M tokens", "note": "blended ~$0.005/min", "free_tier": "free of charge" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "free of charge", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "thinking: docs 'Not supported' vs live thinking=True", "docs: Thinking not supported vs live thinking=true" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.5-transcribe", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - `gemini-3.5-transcribe` (Unary) - `gemini-3.5-transcribe-live` (Live API)", "docs_latest_update": "August 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3.6-flash", "display_name": "Gemini 3.6 Flash", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini 3.6", "generation": "3.6", "description": "Gemini 3.6 Flash", "status": [ "DOCUMENTED", "LIVE_DISCOVERED" ], "lifecycle_docs": "Stable (GA)", "release_date": "2026-07-21", "knowledge_cutoff": "January 2025 (Gemini 3 model cards; not stated on the API model pages)", "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": 1048576, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "thinking": "medium", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": true, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "medium", "thinking_levels": [ "minimal", "low", "medium", "high" ], "thinking_level_param": true, "thinking_budget_legacy_param": false, "thought_signatures": true, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": true, "url_context": true, "code_execution": true, "computer_use": "Supported (Preview)", "file_search": true, "context_caching_explicit": true, "context_caching_docs": true, "context_caching_implicit": true, "batch_api": true, "batch_api_docs": true, "flex_inference": true, "priority_inference": true, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=2)", "batch_enqueued_tokens_tier1_tier2_tier3": [ 3000000, 400000000, 1000000000 ] }, "live_model_metadata": { "name": "models/gemini-3.6-flash", "version": "3.6-flash-07-2026", "displayName": "Gemini 3.6 Flash", "description": "Gemini 3.6 Flash", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-3.6-flash:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-3.6-flash:countTokens", "source": "live supportedGenerationMethods" }, { "name": "createCachedContent", "route": "POST /v1beta/cachedContents (model=models/gemini-3.6-flash)", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-3.6-flash:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-3.6-flash:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-3.6-flash)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "google_maps", "category": "server", "support": true }, { "type": "url_context", "category": "server", "support": true }, { "type": "code_execution", "category": "server", "support": true }, { "type": "computer_use", "category": "server", "support": "Supported (Preview)" }, { "type": "file_search", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "tiers": { "standard": { "input": 0.75, "output": 3.75, "cached_input": 0.075, "cache_storage_hour": 0.5 }, "batch": { "input": 0.375, "output": 1.875, "cached_input": 0.0375, "cache_storage_hour": 0.5 }, "flex": { "input": 0.375, "output": 1.875, "cached_input": 0.0375, "cache_storage_hour": 0.5 }, "priority": { "input": 1.35, "output": 6.75, "cached_input": 0.135, "cache_storage_hour": 0.5 } }, "free_tier": "input/output/caching free of charge (standard & priority rows); Batch/Flex not available", "grounding": { "google_search": "5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)", "google_maps": "5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries" }, "output_includes_thinking_tokens": true, "batch_discount": 0.5, "flex_discount": 0.5, "priority_premium": "1.8x standard (docs: 75-100% more)", "from_2027_01_01": { "standard": { "input": 1.5, "output": 7.5, "cached_input": 0.15, "cache_storage_hour": 1.0 }, "batch": { "input": 0.75, "output": 3.75, "cached_input": 0.075, "cache_storage_hour": 1.0 }, "flex": { "input": 0.75, "output": 3.75, "cached_input": 0.075, "cache_storage_hour": 1.0 }, "priority": { "input": 2.7, "output": 13.5, "cached_input": 0.27, "cache_storage_hour": 1.0 } }, "intro_pricing_note": "Introductory prices through December 31, 2026" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 3000000, "Tier 2": 400000000, "Tier 3": 1000000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "input/output/caching free of charge (standard & priority rows); Batch/Flex not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.6-flash", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Stable: `gemini-3.6-flash`", "model_card": "Model card", "docs_latest_update": "July 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3.7-flash", "display_name": "Gemini 3.7 Flash", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini 3.7", "generation": "3.7", "description": "Gemini 3.7 Flash", "status": [ "DOCUMENTED", "LIVE_DISCOVERED" ], "lifecycle_docs": "Stable (GA)", "release_date": "2026-08-13", "knowledge_cutoff": "January 2025 (Gemini 3 model cards; not stated on the API model pages)", "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": 1048576, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "thinking": "medium", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": true, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "Supported (low, medium, high) Note: `minimal` is not supported and returns an error.", "thinking_live_flag": true, "thinking_default_level": "medium", "thinking_levels": [ "low", "medium", "high" ], "thinking_level_param": true, "thinking_budget_legacy_param": false, "thought_signatures": true, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": true, "url_context": true, "code_execution": true, "computer_use": "Supported (Preview)", "file_search": true, "context_caching_explicit": true, "context_caching_docs": true, "context_caching_implicit": true, "batch_api": true, "batch_api_docs": true, "flex_inference": true, "priority_inference": true, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=2)", "batch_enqueued_tokens_tier1_tier2_tier3": [ 3000000, 400000000, 1000000000 ] }, "live_model_metadata": { "name": "models/gemini-3.7-flash", "version": "3.7-flash-08-2026", "displayName": "Gemini 3.7 Flash", "description": "Gemini 3.7 Flash", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-3.7-flash:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-3.7-flash:countTokens", "source": "live supportedGenerationMethods" }, { "name": "createCachedContent", "route": "POST /v1beta/cachedContents (model=models/gemini-3.7-flash)", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-3.7-flash:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-3.7-flash:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-3.7-flash)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "google_maps", "category": "server", "support": true }, { "type": "url_context", "category": "server", "support": true }, { "type": "code_execution", "category": "server", "support": true }, { "type": "computer_use", "category": "server", "support": "Supported (Preview)" }, { "type": "file_search", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "tiers": { "standard": { "input": 0.75, "output": 3.75, "cached_input": 0.075, "cache_storage_hour": 0.5 }, "batch": { "input": 0.375, "output": 1.875, "cached_input": 0.0375, "cache_storage_hour": 0.5 }, "flex": { "input": 0.375, "output": 1.875, "cached_input": 0.0375, "cache_storage_hour": 0.5 }, "priority": { "input": 1.35, "output": 6.75, "cached_input": 0.135, "cache_storage_hour": 0.5 } }, "free_tier": "input/output/caching free of charge (standard & priority rows); Batch/Flex not available", "grounding": { "google_search": "5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)", "google_maps": "5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries" }, "output_includes_thinking_tokens": true, "batch_discount": 0.5, "flex_discount": 0.5, "priority_premium": "1.8x standard (docs: 75-100% more)", "from_2027_01_01": { "standard": { "input": 1.5, "output": 7.5, "cached_input": 0.15, "cache_storage_hour": 1.0 }, "batch": { "input": 0.75, "output": 3.75, "cached_input": 0.075, "cache_storage_hour": 1.0 }, "flex": { "input": 0.75, "output": 3.75, "cached_input": 0.075, "cache_storage_hour": 1.0 }, "priority": { "input": 2.7, "output": 13.5, "cached_input": 0.27, "cache_storage_hour": 1.0 } }, "intro_pricing_note": "Introductory prices through December 31, 2026" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 3000000, "Tier 2": 400000000, "Tier 3": 1000000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "input/output/caching free of charge (standard & priority rows); Batch/Flex not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.7-flash", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Stable: `gemini-3.7-flash`", "model_card": "Model card", "docs_latest_update": "August 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3.8-flash", "display_name": "Gemini 3.8 Flash", "kind": "stable", "aliases": [ "gemini-flash-latest (observed 2026-09-19 via modelVersion)" ], "snapshots": [], "family": "Gemini 3.8", "generation": "3.8", "description": "Gemini 3.8 Flash", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "LIVE_VERIFIED" ], "lifecycle_docs": "Stable (GA)", "release_date": "2026-09-02", "knowledge_cutoff": "January 2025 (Gemini 3 model cards; not stated on the API model pages)", "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": 1048576, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "thinking": "medium", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": true, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "Supported (low, medium, high) Note: `minimal` is not supported and returns an error.", "thinking_live_flag": true, "thinking_default_level": "medium", "thinking_levels": [ "low", "medium", "high" ], "thinking_level_param": true, "thinking_budget_legacy_param": false, "thought_signatures": true, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": true, "url_context": true, "code_execution": true, "computer_use": "Supported (Preview)", "file_search": true, "context_caching_explicit": true, "context_caching_docs": true, "context_caching_implicit": true, "batch_api": true, "batch_api_docs": true, "flex_inference": true, "priority_inference": true, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=2)", "batch_enqueued_tokens_tier1_tier2_tier3": [ 3000000, 400000000, 1000000000 ] }, "live_model_metadata": { "name": "models/gemini-3.8-flash", "version": "3.0", "displayName": "Gemini 3.8 Flash", "description": "Gemini 3.8 Flash", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-3.8-flash:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-3.8-flash:countTokens", "source": "live supportedGenerationMethods" }, { "name": "createCachedContent", "route": "POST /v1beta/cachedContents (model=models/gemini-3.8-flash)", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-3.8-flash:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-3.8-flash:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-3.8-flash)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "google_maps", "category": "server", "support": true }, { "type": "url_context", "category": "server", "support": true }, { "type": "code_execution", "category": "server", "support": true }, { "type": "computer_use", "category": "server", "support": "Supported (Preview)" }, { "type": "file_search", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "tiers": { "standard": { "input": 0.75, "output": 3.75, "cached_input": 0.075, "cache_storage_hour": 0.5 }, "batch": { "input": 0.375, "output": 1.875, "cached_input": 0.0375, "cache_storage_hour": 0.5 }, "flex": { "input": 0.375, "output": 1.875, "cached_input": 0.0375, "cache_storage_hour": 0.5 }, "priority": { "input": 1.35, "output": 6.75, "cached_input": 0.135, "cache_storage_hour": 0.5 } }, "free_tier": "input/output/caching free of charge (standard & priority rows); Batch/Flex not available", "grounding": { "google_search": "5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)", "google_maps": "5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries" }, "output_includes_thinking_tokens": true, "batch_discount": 0.5, "flex_discount": 0.5, "priority_premium": "1.8x standard (docs: 75-100% more)", "from_2027_01_01": { "standard": { "input": 1.5, "output": 7.5, "cached_input": 0.15, "cache_storage_hour": 1.0 }, "batch": { "input": 0.75, "output": 3.75, "cached_input": 0.075, "cache_storage_hour": 1.0 }, "flex": { "input": 0.75, "output": 3.75, "cached_input": 0.075, "cache_storage_hour": 1.0 }, "priority": { "input": 2.7, "output": 13.5, "cached_input": 0.27, "cache_storage_hour": 1.0 } }, "intro_pricing_note": "Introductory prices through December 31, 2026" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 3000000, "Tier 2": 400000000, "Tier 3": 1000000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "input/output/caching free of charge (standard & priority rows); Batch/Flex not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "live version field is '3.0' (other 3.x GA models carry dated versions like 3.7-flash-08-2026)" ], "last_verified": "2026-09-19", "verification": { "method": "live_api", "verified_at": "2026-09-19T00:00:00Z", "result": "success", "http_status": null, "request_note": "POST :generateContent -> 200 (modelVersion=gemini-3.8-flash)" }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Stable: `gemini-3.8-flash`", "model_card": "Model card", "docs_latest_update": "September 2026", "generate_content_probe": { "http_status": 200, "request": "generateContent 'Reply with OK.' maxOutputTokens=8", "modelVersion": "gemini-3.8-flash", "responseId_present": true, "finishReason": "MAX_TOKENS", "usageMetadata": { "promptTokenCount": 5, "totalTokenCount": 10, "promptTokensDetails": [ { "modality": "TEXT", "tokenCount": 5 } ], "thoughtsTokenCount": 5, "serviceTier": "standard" }, "thoughtSignature_present": false, "text": "", "response_headers": { "Server-Timing": "gfet4t7; dur=2191" }, "header_names": [ "Accept-Ranges", "Alt-Svc", "Connection", "Content-Type", "Date", "Server", "Server-Timing", "Transfer-Encoding", "Vary", "X-Content-Type-Options", "X-Frame-Options", "X-Gemini-Service-Tier", "X-XSS-Protection" ] }, "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "lyria-3-clip-preview", "display_name": "Lyria 3 Clip Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Lyria", "generation": "3", "description": "Lyria 3 30s model Preview", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW" ], "lifecycle_docs": "Preview", "release_date": "2026-03-25", "knowledge_cutoff": null, "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": 131072, "docs_output_token_limit": null, "modalities": { "input": [ "text", "image" ], "output": [ "audio (music)", "text (lyrics)" ] }, "thinking": "not supported", "capabilities": { "text_input": true, "image_input": true, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": false, "image_output": false, "audio_output": true, "video_output": false, "music_output": true, "embeddings": false, "thinking": false, "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": false, "function_calling": false, "parallel_function_calling": false, "compositional_function_calling": false, "google_search_grounding": false, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": false, "flex_inference": false, "priority_inference": false, "live_api": false, "tts": false, "audio_generation_docs": true, "image_generation": false, "video_generation": false, "music_generation": true, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": true, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/lyria-3-clip-preview", "version": "lyria-3-clip-preview", "displayName": "Lyria 3 Clip Preview", "description": "Lyria 3 30s model Preview", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "thinking": null, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/lyria-3-clip-preview:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/lyria-3-clip-preview:countTokens", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/lyria-3-clip-preview:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=lyria-3-clip-preview)", "source": "docs (music-generation.md / omni.md use the Interactions API)" } ], "tools": [], "pricing": { "currency": "USD", "per_request": 0.04, "unit": "per song (30 s clip)", "free_tier": "not available" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "inputTokenLimit live=1048576 vs docs=131072" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/lyria-3-clip-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Preview: `lyria-3-clip-preview` - Preview: `lyria-3-pro-preview`", "docs_latest_update": "March 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "lyria-3-pro-preview", "display_name": "Lyria 3 Pro Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Lyria", "generation": "3", "description": "Lyria 3 Pro Preview", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW" ], "lifecycle_docs": "Preview", "release_date": "2026-03-25", "knowledge_cutoff": null, "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": 131072, "docs_output_token_limit": null, "modalities": { "input": [ "text", "image" ], "output": [ "audio (music)", "text (lyrics)" ] }, "thinking": "not supported", "capabilities": { "text_input": true, "image_input": true, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": false, "image_output": false, "audio_output": true, "video_output": false, "music_output": true, "embeddings": false, "thinking": false, "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": false, "function_calling": false, "parallel_function_calling": false, "compositional_function_calling": false, "google_search_grounding": false, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": false, "flex_inference": false, "priority_inference": false, "live_api": false, "tts": false, "audio_generation_docs": true, "image_generation": false, "video_generation": false, "music_generation": true, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": true, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/lyria-3-pro-preview", "version": "lyria-3-pro-preview", "displayName": "Lyria 3 Pro Preview", "description": "Lyria 3 Pro Preview", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "thinking": null, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/lyria-3-pro-preview:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/lyria-3-pro-preview:countTokens", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/lyria-3-pro-preview:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=lyria-3-pro-preview)", "source": "docs (music-generation.md / omni.md use the Interactions API)" } ], "tools": [], "pricing": { "currency": "USD", "per_request": 0.08, "unit": "per song (full length)", "free_tier": "not available" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "inputTokenLimit live=1048576 vs docs=131072" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/lyria-3-pro-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Preview: `lyria-3-clip-preview` - Preview: `lyria-3-pro-preview`", "docs_latest_update": "March 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "lyria-3.5", "display_name": "Lyria 3.5", "kind": "stable", "aliases": [], "snapshots": [], "family": "Lyria", "generation": "3.5", "description": "Music Generation model", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "LIVE_VERIFIED" ], "lifecycle_docs": "Stable (GA)", "release_date": "2026-09-03", "knowledge_cutoff": null, "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": 131072, "docs_output_token_limit": null, "modalities": { "input": [ "text", "image" ], "output": [ "audio (music)", "text (lyrics)" ] }, "thinking": "not supported", "capabilities": { "text_input": true, "image_input": true, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": false, "image_output": false, "audio_output": true, "video_output": false, "music_output": true, "embeddings": false, "thinking": false, "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": false, "function_calling": false, "parallel_function_calling": false, "compositional_function_calling": false, "google_search_grounding": false, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": false, "flex_inference": false, "priority_inference": false, "live_api": false, "tts": false, "audio_generation_docs": true, "image_generation": false, "video_generation": false, "music_generation": true, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": "unknown", "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/lyria-3.5", "version": "3.5", "displayName": "Lyria 3.5", "description": "Music Generation model", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "thinking": null, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/lyria-3.5:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/lyria-3.5:countTokens", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/lyria-3.5:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=lyria-3.5)", "source": "docs (music-generation.md / omni.md use the Interactions API)" } ], "tools": [], "pricing": { "currency": "USD", "per_request": 0.08, "unit": "per song (full length)", "free_tier": "not available" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "inputTokenLimit live=1048576 vs docs=131072" ], "last_verified": "2026-09-19", "verification": { "method": "live_api", "verified_at": "2026-09-19T00:00:00Z", "result": "success", "http_status": 200, "request_note": "GET /v1beta/models/lyria-3.5 -> 200" }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/lyria-3.5", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Stable: `lyria-3.5`", "docs_latest_update": "September 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3.1-flash-tts-preview", "display_name": "Gemini 3.1 Flash TTS Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 3.1", "generation": "3.1", "description": "Gemini 3.1 Flash TTS Preview", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW" ], "lifecycle_docs": "Preview", "release_date": "2026-04-13", "knowledge_cutoff": "January 2025 (Gemini 3 model cards; not stated on the API model pages)", "context_window": 8192, "max_output": 16384, "docs_input_token_limit": 8192, "docs_output_token_limit": 16384, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "thinking": "not supported", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": false, "image_output": false, "audio_output": true, "video_output": false, "music_output": false, "embeddings": false, "thinking": false, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": false, "function_calling": false, "parallel_function_calling": false, "compositional_function_calling": false, "google_search_grounding": false, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": true, "flex_inference": false, "priority_inference": false, "live_api": false, "tts": true, "audio_generation_docs": true, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=2)", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemini-3.1-flash-tts-preview", "version": "3.1-flash-tts-preview", "displayName": "Gemini 3.1 Flash TTS Preview", "description": "Gemini 3.1 Flash TTS Preview", "inputTokenLimit": 8192, "outputTokenLimit": 16384, "supportedGenerationMethods": [ "generateContent", "countTokens", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-3.1-flash-tts-preview:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-3.1-flash-tts-preview:countTokens", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-3.1-flash-tts-preview:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-3.1-flash-tts-preview:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-3.1-flash-tts-preview)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [], "pricing": { "currency": "USD", "input_text": 1.0, "output_audio": 20.0, "batch": { "input_text": 0.5, "output_audio": 10.0 }, "unit": "per 1M tokens", "note": "25 audio tokens per second", "free_tier": "free of charge (standard); batch not available" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "free of charge (standard); batch not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "thinking: docs 'Not supported' vs live thinking=True" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-tts-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - `gemini-3.1-flash-tts-preview`", "model_card": "Model card", "docs_latest_update": "April 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-robotics-er-2-preview", "display_name": "Gemini Robotics-ER 2 Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini Robotics-ER", "generation": "2", "description": "Gemini Robotics-ER 2 Preview", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW" ], "lifecycle_docs": "Preview", "release_date": "2026-07-30", "knowledge_cutoff": "January 2025", "context_window": 131072, "max_output": 65536, "docs_input_token_limit": 131072, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": true, "url_context": true, "code_execution": true, "computer_use": true, "file_search": true, "context_caching_explicit": true, "context_caching_docs": true, "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": true, "flex_inference": false, "priority_inference": false, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": "unknown", "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemini-robotics-er-2-preview", "version": "2-preview", "displayName": "Gemini Robotics-ER 2 Preview", "description": "Gemini Robotics-ER 2 Preview", "inputTokenLimit": 131072, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-robotics-er-2-preview:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-robotics-er-2-preview:countTokens", "source": "live supportedGenerationMethods" }, { "name": "createCachedContent", "route": "POST /v1beta/cachedContents (model=models/gemini-robotics-er-2-preview)", "source": "live supportedGenerationMethods" }, { "name": "batchGenerateContent", "route": "POST /v1beta/models/gemini-robotics-er-2-preview:batchGenerateContent", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-robotics-er-2-preview:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-robotics-er-2-preview)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "google_maps", "category": "server", "support": true }, { "type": "url_context", "category": "server", "support": true }, { "type": "code_execution", "category": "server", "support": true }, { "type": "computer_use", "category": "server", "support": true }, { "type": "file_search", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "tiers": { "standard": { "input": 1.0, "output": 5.0, "cached_input": 0.1, "cache_storage_hour": 0.5 }, "batch": { "input": 0.5, "output": 2.5, "cached_input": 0.05, "cache_storage_hour": 0.5 } }, "free_tier": "input/output free of charge; caching not available", "grounding": { "google_search": "5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)", "google_maps": "5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries" }, "output_includes_thinking_tokens": true, "batch_discount": 0.5, "flex_discount": 0.5, "priority_premium": "1.8x standard (docs: 75-100% more)", "from_2027_01_01": { "standard": { "input": 2.0, "output": 10.0, "cached_input": 0.2, "cache_storage_hour": 1.0 }, "batch": { "input": 1.0, "output": 5.0, "cached_input": 0.1, "cache_storage_hour": 1.0 } }, "intro_pricing_note": "Introductory prices through December 31, 2026", "input_note": "text / image / video / audio same price" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "input/output free of charge; caching not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-robotics-er-2-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Preview: `gemini-robotics-er-1.6-preview`", "model_card": "Model card", "docs_latest_update": "December 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.5-computer-use-preview-10-2025", "display_name": "Gemini 2.5 Computer Use Preview 10-2025", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 2.5", "generation": "2.5", "description": "Gemini 2.5 Computer Use Preview 10-2025", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW" ], "lifecycle_docs": "Preview", "release_date": "2025-10-07", "knowledge_cutoff": null, "context_window": 131072, "max_output": 65536, "docs_input_token_limit": 128000, "docs_output_token_limit": 64000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": true, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": true, "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": "unknown", "context_caching_implicit": true, "batch_api": false, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": "unknown", "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": true, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemini-2.5-computer-use-preview-10-2025", "version": "Gemini 2.5 Computer Use Preview 10-2025", "displayName": "Gemini 2.5 Computer Use Preview 10-2025", "description": "Gemini 2.5 Computer Use Preview 10-2025", "inputTokenLimit": 131072, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/gemini-2.5-computer-use-preview-10-2025:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-2.5-computer-use-preview-10-2025:countTokens", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/gemini-2.5-computer-use-preview-10-2025:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (model=gemini-2.5-computer-use-preview-10-2025)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [ { "type": "computer_use", "category": "server", "support": true } ], "pricing": { "currency": "USD", "unit": "per 1M tokens", "tiers": { "standard": { "input": 1.0, "output": 5.0 } }, "free_tier": "input/output free of charge", "grounding": { "google_search": "5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)", "google_maps": "5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries" }, "output_includes_thinking_tokens": true, "batch_discount": 0.5, "flex_discount": 0.5, "priority_premium": "1.8x standard (docs: 75-100% more)", "from_2027_01_01": { "standard": { "input": 2.0, "output": 10.0, "cached_input": null, "cache_storage_hour": null } }, "intro_pricing_note": "Introductory prices through December 31, 2026", "extra_note": "pricing.md also shows an unlabeled second table ($1.25/$2.50 input, $10/$15 output, <=200k / >200k) under this heading; likely stale legacy rates" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "input/output free of charge", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "inputTokenLimit live=131072 vs docs=128000", "outputTokenLimit live=65536 vs docs=64000" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-computer-use-preview-10-2025", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Preview: `gemini-2.5-computer-use-preview-10-2025`", "docs_latest_update": "October 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "antigravity-preview-05-2026", "display_name": "Antigravity Agent Preview", "kind": "agent", "aliases": [], "snapshots": [], "family": "Antigravity (managed agent)", "generation": null, "description": "Preview release of Antigravity Agent (05-2026)", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW", "DEPRECATED" ], "lifecycle_docs": "Deprecated (shutdown scheduled)", "release_date": "2026-05-19", "knowledge_cutoff": null, "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": 1048576, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "thinking": "not supported", "capabilities": { "text_input": true, "image_input": true, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": false, "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": false, "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": true, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=None topP=None topK=None maxTemperature=None", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/antigravity-preview-05-2026", "version": "0.1", "displayName": "Antigravity Agent Preview", "description": "Preview release of Antigravity Agent (05-2026)", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "thinking": null, "temperature": null, "topP": null, "topK": null, "maxTemperature": null }, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/antigravity-preview-05-2026:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/antigravity-preview-05-2026:countTokens", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/antigravity-preview-05-2026:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (agent=antigravity-preview-05-2026)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [], "pricing": "agent: all model inference at standard Gemini list rates (input, output, intermediate/reasoning tokens); tools per tool pricing; sandbox compute not billed during preview", "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2026-05-19", "earliest_shutdown": "2026-10-05", "replacement": "antigravity-preview-09-2026", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/antigravity-preview-05-2026", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Preview: `antigravity-preview-05-2026`", "docs_latest_update": "May 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "antigravity-preview-09-2026", "display_name": "Antigravity Agent Preview", "kind": "agent", "aliases": [], "snapshots": [], "family": "Antigravity (managed agent)", "generation": null, "description": "Preview release of Antigravity Agent (09-2026)", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW" ], "lifecycle_docs": "Agent", "release_date": "2026-09-17", "knowledge_cutoff": null, "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "not supported", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": false, "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": true, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=None topP=None topK=None maxTemperature=None", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/antigravity-preview-09-2026", "version": "0.1", "displayName": "Antigravity Agent Preview", "description": "Preview release of Antigravity Agent (09-2026)", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "thinking": null, "temperature": null, "topP": null, "topK": null, "maxTemperature": null }, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/antigravity-preview-09-2026:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/antigravity-preview-09-2026:countTokens", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/antigravity-preview-09-2026:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (agent=antigravity-preview-09-2026)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [], "pricing": "agent: all model inference at standard Gemini list rates (input, output, intermediate/reasoning tokens); tools per tool pricing; sandbox compute not billed during preview", "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "live-listed id without a dedicated docs model page" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "deep-research-max-preview-04-2026", "display_name": "Deep Research Max Preview (Apr-21-2026)", "kind": "agent", "aliases": [], "snapshots": [], "family": "Deep Research (agent)", "generation": null, "description": "Preview release (April 21st, 2026) of Deep Research Max", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW" ], "lifecycle_docs": "Agent", "release_date": "2026-04-21", "knowledge_cutoff": null, "context_window": 131072, "max_output": 65536, "docs_input_token_limit": 1048576, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text", "image" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": true, "text_output": true, "image_output": true, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": false, "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": true, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": true, "deep_research_agent": true, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/deep-research-max-preview-04-2026", "version": "deepthink-exp-05-20", "displayName": "Deep Research Max Preview (Apr-21-2026)", "description": "Preview release (April 21st, 2026) of Deep Research Max", "inputTokenLimit": 131072, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/deep-research-max-preview-04-2026:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/deep-research-max-preview-04-2026:countTokens", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/deep-research-max-preview-04-2026:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (agent=deep-research-max-preview-04-2026)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [], "pricing": "agent: all model inference at standard Gemini list rates (input, output, intermediate/reasoning tokens); tools per tool pricing; sandbox compute not billed during preview", "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "inputTokenLimit live=131072 vs docs=1048576", "live version 'deepthink-exp-05-20' and inputTokenLimit 131,072 vs docs 'Input context window 1,048,576'" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/deep-research-max-preview-04-2026", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Preview: `deep-research-max-preview-04-2026`", "docs_latest_update": "April 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "deep-research-preview-04-2026", "display_name": "Deep Research Preview (Apr-21-2026)", "kind": "agent", "aliases": [], "snapshots": [], "family": "Deep Research (agent)", "generation": null, "description": "Preview release (April 21th, 2026) of Deep Research", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW", "LIVE_VERIFIED" ], "lifecycle_docs": "Agent", "release_date": "2026-04-21", "knowledge_cutoff": null, "context_window": 131072, "max_output": 65536, "docs_input_token_limit": 1048576, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text", "image" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": true, "text_output": true, "image_output": true, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": false, "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": true, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": true, "deep_research_agent": true, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/deep-research-preview-04-2026", "version": "deepthink-exp-05-20", "displayName": "Deep Research Preview (Apr-21-2026)", "description": "Preview release (April 21th, 2026) of Deep Research", "inputTokenLimit": 131072, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/deep-research-preview-04-2026:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/deep-research-preview-04-2026:countTokens", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/deep-research-preview-04-2026:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (agent=deep-research-preview-04-2026)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [], "pricing": "agent: all model inference at standard Gemini list rates (input, output, intermediate/reasoning tokens); tools per tool pricing; sandbox compute not billed during preview", "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "inputTokenLimit live=131072 vs docs=1048576", "live version 'deepthink-exp-05-20' and inputTokenLimit 131,072 vs docs 'Input context window 1,048,576'" ], "last_verified": "2026-09-19", "verification": { "method": "live_api", "verified_at": "2026-09-19T00:00:00Z", "result": "success", "http_status": 200, "request_note": "GET /v1beta/models/deep-research-preview-04-2026 -> 200" }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/deep-research-preview-04-2026", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Preview: `deep-research-preview-04-2026` - Max: `deep-research-max-preview-04-2026`", "docs_latest_update": "April 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "deep-research-pro-preview-12-2025", "display_name": "Deep Research Pro Preview (Dec-12-2025)", "kind": "agent", "aliases": [], "snapshots": [], "family": "Deep Research (agent)", "generation": null, "description": "Preview release (December 12th, 2025) of Deep Research Pro", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW" ], "lifecycle_docs": "Agent", "release_date": "2025-12-12", "knowledge_cutoff": null, "context_window": 131072, "max_output": 65536, "docs_input_token_limit": 1048576, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": true, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": false, "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": true, "interactions_api_listed_in_docs_table": true, "deep_research_agent": true, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": true, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/deep-research-pro-preview-12-2025", "version": "deepthink-exp-05-20", "displayName": "Deep Research Pro Preview (Dec-12-2025)", "description": "Preview release (December 12th, 2025) of Deep Research Pro", "inputTokenLimit": 131072, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "endpoints": [ { "name": "generateContent", "route": "POST /v1beta/models/deep-research-pro-preview-12-2025:generateContent", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/deep-research-pro-preview-12-2025:countTokens", "source": "live supportedGenerationMethods" }, { "name": "streamGenerateContent", "route": "POST /v1beta/models/deep-research-pro-preview-12-2025:streamGenerateContent?alt=sse", "source": "implied by generateContent (not listed in supportedGenerationMethods)" }, { "name": "interactions", "route": "POST /v1beta/interactions (agent=deep-research-pro-preview-12-2025)", "source": "docs (Interactions API); GA in v1 for models" } ], "tools": [], "pricing": "agent: all model inference at standard Gemini list rates (input, output, intermediate/reasoning tokens); tools per tool pricing; sandbox compute not billed during preview", "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "inputTokenLimit live=131072 vs docs=1048576", "live version 'deepthink-exp-05-20' and inputTokenLimit 131,072 vs docs 'Input context window 1,048,576'" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/deep-research-pro-preview-12-2025", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Preview: `deep-research-pro-preview-12-2025`", "docs_latest_update": "December 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-embedding-001", "display_name": "Gemini Embedding 001", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini Embedding", "generation": "001", "description": "Obtain a distributed representation of a text.", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "DEPRECATED" ], "lifecycle_docs": "Deprecated (shutdown scheduled)", "release_date": "2025-07-14", "knowledge_cutoff": null, "context_window": 2048, "max_output": 1, "docs_input_token_limit": 2048, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "thinking": "not supported", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": false, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": true, "thinking": false, "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": false, "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": true, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "live defaults temperature=None topP=None topK=None maxTemperature=None", "batch_enqueued_tokens_tier1_tier2_tier3": [ 500000, 5000000, 10000000 ], "embedding_dimensions": "flexible 128-3072 (recommended 768, 1536, 3072; default 3072, MRL truncation; embedding-2 auto-renormalizes)", "embedding_task_type_param": true, "embedding_input_token_limit": 2048 }, "live_model_metadata": { "name": "models/gemini-embedding-001", "version": "001", "displayName": "Gemini Embedding 001", "description": "Obtain a distributed representation of a text.", "inputTokenLimit": 2048, "outputTokenLimit": 1, "supportedGenerationMethods": [ "embedContent", "countTextTokens", "countTokens", "asyncBatchEmbedContent" ], "thinking": null, "temperature": null, "topP": null, "topK": null, "maxTemperature": null }, "supportedGenerationMethods": [ "embedContent", "countTextTokens", "countTokens", "asyncBatchEmbedContent" ], "endpoints": [ { "name": "embedContent", "route": "POST /v1beta/models/gemini-embedding-001:embedContent", "source": "live supportedGenerationMethods" }, { "name": "countTextTokens", "route": "POST /v1beta/models/gemini-embedding-001:countTextTokens (legacy PaLM method)", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-embedding-001:countTokens", "source": "live supportedGenerationMethods" }, { "name": "asyncBatchEmbedContent", "route": "POST /v1beta/models/gemini-embedding-001:asyncBatchEmbedContent", "source": "live supportedGenerationMethods" } ], "tools": [], "pricing": "not listed on pricing.md (2026-09-18); file-search.md bills indexing embeddings at $0.15 per 1M tokens", "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 500000, "Tier 2": 5000000, "Tier 3": 10000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-07-14", "earliest_shutdown": "2028-05-14", "replacement": "gemini-embedding-2", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-embedding-001", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Stable: `gemini-embedding-001`", "docs_latest_update": "June 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-embedding-2-preview", "display_name": "Gemini Embedding 2 Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini Embedding", "generation": "2", "description": "Obtain a distributed representation of multimodal content.", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW" ], "lifecycle_docs": "Preview", "release_date": "2026-03-10", "knowledge_cutoff": null, "context_window": 8192, "max_output": 1, "docs_input_token_limit": 8192, "docs_output_token_limit": null, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "embedding" ] }, "thinking": "not supported", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": true, "text_output": false, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": true, "thinking": false, "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": false, "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": true, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "live defaults temperature=None topP=None topK=None maxTemperature=None", "batch_enqueued_tokens_tier1_tier2_tier3": [ 500000, 5000000, 10000000 ], "embedding_dimensions": "flexible 128-3072 (recommended 768, 1536, 3072; default 3072, MRL truncation; embedding-2 auto-renormalizes)", "embedding_task_type_param": false, "embedding_input_token_limit": 8192 }, "live_model_metadata": { "name": "models/gemini-embedding-2-preview", "version": "2", "displayName": "Gemini Embedding 2 Preview", "description": "Obtain a distributed representation of multimodal content.", "inputTokenLimit": 8192, "outputTokenLimit": 1, "supportedGenerationMethods": [ "embedContent", "countTextTokens", "countTokens", "asyncBatchEmbedContent" ], "thinking": null, "temperature": null, "topP": null, "topK": null, "maxTemperature": null }, "supportedGenerationMethods": [ "embedContent", "countTextTokens", "countTokens", "asyncBatchEmbedContent" ], "endpoints": [ { "name": "embedContent", "route": "POST /v1beta/models/gemini-embedding-2-preview:embedContent", "source": "live supportedGenerationMethods" }, { "name": "countTextTokens", "route": "POST /v1beta/models/gemini-embedding-2-preview:countTextTokens (legacy PaLM method)", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-embedding-2-preview:countTokens", "source": "live supportedGenerationMethods" }, { "name": "asyncBatchEmbedContent", "route": "POST /v1beta/models/gemini-embedding-2-preview:asyncBatchEmbedContent", "source": "live supportedGenerationMethods" } ], "tools": [], "pricing": { "currency": "USD", "input_text": 0.2, "input_image": 0.45, "input_image_per_image": 0.00012, "input_audio": 6.5, "input_audio_per_second": 0.00016, "input_video": 12.0, "input_video_per_frame": 0.00079, "batch": { "input_text": 0.1, "input_image": 0.225, "input_audio": 3.25, "input_video": 6.0 }, "unit": "per 1M tokens", "free_tier": "free of charge (standard); batch not available", "same_as": "gemini-embedding-2" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 500000, "Tier 2": 5000000, "Tier 3": 10000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "free of charge (standard); batch not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-embedding-2-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Preview: `gemini-embedding-2-preview`", "docs_latest_update": "March 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-embedding-2", "display_name": "Gemini Embedding 2", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini Embedding", "generation": "2", "description": "Obtain a distributed representation of multimodal content.", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "LIVE_VERIFIED" ], "lifecycle_docs": "Stable (GA)", "release_date": "2026-04-22", "knowledge_cutoff": null, "context_window": 8192, "max_output": 1, "docs_input_token_limit": 8192, "docs_output_token_limit": null, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "embedding" ] }, "thinking": "not supported", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": true, "text_output": false, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": true, "thinking": false, "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": false, "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": true, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "live defaults temperature=None topP=None topK=None maxTemperature=None", "batch_enqueued_tokens_tier1_tier2_tier3": [ 500000, 5000000, 10000000 ], "embedding_dimensions": "flexible 128-3072 (recommended 768, 1536, 3072; default 3072, MRL truncation; embedding-2 auto-renormalizes)", "embedding_task_type_param": false, "embedding_input_token_limit": 8192 }, "live_model_metadata": { "name": "models/gemini-embedding-2", "version": "2", "displayName": "Gemini Embedding 2", "description": "Obtain a distributed representation of multimodal content.", "inputTokenLimit": 8192, "outputTokenLimit": 1, "supportedGenerationMethods": [ "embedContent", "countTextTokens", "countTokens", "asyncBatchEmbedContent" ], "thinking": null, "temperature": null, "topP": null, "topK": null, "maxTemperature": null }, "supportedGenerationMethods": [ "embedContent", "countTextTokens", "countTokens", "asyncBatchEmbedContent" ], "endpoints": [ { "name": "embedContent", "route": "POST /v1beta/models/gemini-embedding-2:embedContent", "source": "live supportedGenerationMethods" }, { "name": "countTextTokens", "route": "POST /v1beta/models/gemini-embedding-2:countTextTokens (legacy PaLM method)", "source": "live supportedGenerationMethods" }, { "name": "countTokens", "route": "POST /v1beta/models/gemini-embedding-2:countTokens", "source": "live supportedGenerationMethods" }, { "name": "asyncBatchEmbedContent", "route": "POST /v1beta/models/gemini-embedding-2:asyncBatchEmbedContent", "source": "live supportedGenerationMethods" } ], "tools": [], "pricing": { "currency": "USD", "input_text": 0.2, "input_image": 0.45, "input_image_per_image": 0.00012, "input_audio": 6.5, "input_audio_per_second": 0.00016, "input_video": 12.0, "input_video_per_frame": 0.00079, "batch": { "input_text": 0.1, "input_image": 0.225, "input_audio": 3.25, "input_video": 6.0 }, "unit": "per 1M tokens", "free_tier": "free of charge (standard); batch not available" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": { "Tier 1": 500000, "Tier 2": 5000000, "Tier 3": 10000000 }, "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": true, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "free of charge (standard); batch not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "live_api", "verified_at": "2026-09-19T00:00:00Z", "result": "success", "http_status": 200, "request_note": "GET /v1beta/models/gemini-embedding-2 -> 200" }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-embedding-2", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Stable: `gemini-embedding-2`", "docs_latest_update": "April 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "aqa", "display_name": "Model that performs Attributed Question Answering.", "kind": "stable", "aliases": [], "snapshots": [], "family": "AQA (Attributed Question Answering)", "generation": null, "description": "Model trained to return answers to questions that are grounded in provided sources, along with estimating answerable probability.", "status": [ "LIVE_DISCOVERED" ], "lifecycle_docs": "Stable (GA)", "release_date": null, "knowledge_cutoff": null, "context_window": 7168, "max_output": 1024, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "not supported", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": false, "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "live defaults temperature=0.2 topP=1 topK=40 maxTemperature=None", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/aqa", "version": "001", "displayName": "Model that performs Attributed Question Answering.", "description": "Model trained to return answers to questions that are grounded in provided sources, along with estimating answerable probability.", "inputTokenLimit": 7168, "outputTokenLimit": 1024, "supportedGenerationMethods": [ "generateAnswer" ], "thinking": null, "temperature": 0.2, "topP": 1, "topK": 40, "maxTemperature": null }, "supportedGenerationMethods": [ "generateAnswer" ], "endpoints": [ { "name": "generateAnswer", "route": "POST /v1beta/models/aqa:generateAnswer", "source": "live supportedGenerationMethods" } ], "tools": [], "pricing": "not listed on pricing.md", "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "live-listed id without a dedicated docs model page (aqa: legacy generateAnswer-only model, undocumented)" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "veo-3.1-generate-preview", "display_name": "Veo 3.1", "kind": "preview", "aliases": [], "snapshots": [], "family": "Veo", "generation": "3.1", "description": "Veo 3.1", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW" ], "lifecycle_docs": "Preview", "release_date": "2025-10-15", "knowledge_cutoff": null, "context_window": 480, "max_output": 8192, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text", "image" ], "output": [ "video (with native audio)" ] }, "thinking": "not supported", "capabilities": { "text_input": true, "image_input": true, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": false, "image_output": false, "audio_output": false, "video_output": true, "music_output": false, "embeddings": false, "thinking": false, "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": false, "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": true, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": true, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "live defaults temperature=None topP=None topK=None maxTemperature=None", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/veo-3.1-generate-preview", "version": "3.1", "displayName": "Veo 3.1", "description": "Veo 3.1", "inputTokenLimit": 480, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "predictLongRunning" ], "thinking": null, "temperature": null, "topP": null, "topK": null, "maxTemperature": null }, "supportedGenerationMethods": [ "predictLongRunning" ], "endpoints": [ { "name": "predictLongRunning", "route": "POST /v1beta/models/veo-3.1-generate-preview:predictLongRunning (+ GET /v1beta/{operation})", "source": "live supportedGenerationMethods" } ], "tools": [], "pricing": { "currency": "USD", "per_second": { "720p": 0.4, "1080p": 0.4, "4k": 0.6 }, "unit": "per second of generated video (with audio)", "free_tier": "not available", "note": "charged only if the video is successfully generated" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/veo-3.1-generate-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_latest_update": "January 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "veo-3.1-fast-generate-preview", "display_name": "Veo 3.1 fast", "kind": "preview", "aliases": [], "snapshots": [], "family": "Veo", "generation": "3.1", "description": "Veo 3.1 fast", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW" ], "lifecycle_docs": "Preview", "release_date": "2025-10-15", "knowledge_cutoff": null, "context_window": 480, "max_output": 8192, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text", "image" ], "output": [ "video (with native audio)" ] }, "thinking": "not supported", "capabilities": { "text_input": true, "image_input": true, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": false, "image_output": false, "audio_output": false, "video_output": true, "music_output": false, "embeddings": false, "thinking": false, "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": false, "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": true, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "live defaults temperature=None topP=None topK=None maxTemperature=None", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/veo-3.1-fast-generate-preview", "version": "3.1", "displayName": "Veo 3.1 fast", "description": "Veo 3.1 fast", "inputTokenLimit": 480, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "predictLongRunning" ], "thinking": null, "temperature": null, "topP": null, "topK": null, "maxTemperature": null }, "supportedGenerationMethods": [ "predictLongRunning" ], "endpoints": [ { "name": "predictLongRunning", "route": "POST /v1beta/models/veo-3.1-fast-generate-preview:predictLongRunning (+ GET /v1beta/{operation})", "source": "live supportedGenerationMethods" } ], "tools": [], "pricing": { "currency": "USD", "per_second": { "720p": 0.1, "1080p": 0.12, "4k": 0.3 }, "unit": "per second", "free_tier": "not available" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/veo-3.1-generate-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_latest_update": "January 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "veo-3.1-lite-generate-preview", "display_name": "Veo 3.1 lite", "kind": "preview", "aliases": [], "snapshots": [], "family": "Veo", "generation": "3.1", "description": "Veo 3.1 lite", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW", "LIVE_VERIFIED" ], "lifecycle_docs": "Preview", "release_date": "2026-03-31", "knowledge_cutoff": null, "context_window": 480, "max_output": 8192, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text", "image" ], "output": [ "video (with native audio)" ] }, "thinking": "not supported", "capabilities": { "text_input": true, "image_input": true, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": false, "image_output": false, "audio_output": false, "video_output": true, "music_output": false, "embeddings": false, "thinking": false, "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": false, "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": true, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "live defaults temperature=None topP=None topK=None maxTemperature=None", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/veo-3.1-lite-generate-preview", "version": "3.1", "displayName": "Veo 3.1 lite", "description": "Veo 3.1 lite", "inputTokenLimit": 480, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "predictLongRunning" ], "thinking": null, "temperature": null, "topP": null, "topK": null, "maxTemperature": null }, "supportedGenerationMethods": [ "predictLongRunning" ], "endpoints": [ { "name": "predictLongRunning", "route": "POST /v1beta/models/veo-3.1-lite-generate-preview:predictLongRunning (+ GET /v1beta/{operation})", "source": "live supportedGenerationMethods" } ], "tools": [], "pricing": { "currency": "USD", "per_second": { "720p": 0.05, "1080p": 0.08, "4k": "not supported" }, "unit": "per second", "free_tier": "not available" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "not available", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "live_api", "verified_at": "2026-09-19T00:00:00Z", "result": "success", "http_status": 200, "request_note": "GET /v1beta/models/veo-3.1-lite-generate-preview -> 200" }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/veo-3.1-lite-generate-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_latest_update": "March 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3.5-transcribe-live", "display_name": "Gemini 3.5 Transcribe Live", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini 3.5", "generation": "3.5", "description": "Gemini 3.5 Transcribe Live", "status": [ "DOCUMENTED", "LIVE_DISCOVERED" ], "lifecycle_docs": "Stable (GA)", "release_date": "2026-08", "knowledge_cutoff": "January 2025 (Gemini 3 model cards; not stated on the API model pages)", "context_window": 131072, "max_output": 65536, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "thinking": "not supported", "capabilities": { "text_input": false, "image_input": false, "audio_input": true, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": false, "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": false, "parallel_function_calling": false, "compositional_function_calling": false, "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": false, "flex_inference": false, "priority_inference": false, "live_api": true, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": true, "live_translation": false, "speaker_diarization": true, "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=2)", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemini-3.5-transcribe-live", "version": "3.5-transcribe-live-08-2026", "displayName": "Gemini 3.5 Transcribe Live", "description": "Gemini 3.5 Transcribe Live", "inputTokenLimit": 131072, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "bidiGenerateContent" ], "thinking": null, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "bidiGenerateContent" ], "endpoints": [ { "name": "bidiGenerateContent", "route": "WSS /ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent (Live API)", "source": "live supportedGenerationMethods" } ], "tools": [], "pricing": { "currency": "USD", "input_audio": 3.5, "input_audio_per_min": 0.005, "output_text": 21.0, "output_text_per_min": 0.004, "unit": "per 1M tokens", "note": "25 audio tokens/s input, 175 text tokens/min output; blended ~$0.009/min", "free_tier": "free of charge" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "free of charge", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.5-transcribe", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - `gemini-3.5-transcribe` (Unary) - `gemini-3.5-transcribe-live` (Live API)", "docs_latest_update": "August 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.5-flash-native-audio-latest", "display_name": "Gemini 2.5 Flash Native Audio Latest", "kind": "alias", "aliases": [ { "resolves_to_live": "unknown (Live API only, not probed)", "evidence": "GET /v1beta/models listing", "history": [], "alias": "gemini-2.5-flash-native-audio-latest" } ], "snapshots": [], "family": "Gemini (latest alias)", "generation": null, "description": "Latest release of Gemini 2.5 Flash Native Audio", "status": [ "LIVE_DISCOVERED" ], "lifecycle_docs": "Alias", "release_date": null, "knowledge_cutoff": null, "context_window": 131072, "max_output": 8192, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": true, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": true, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemini-2.5-flash-native-audio-latest", "version": "Gemini 2.5 Flash Native Audio Latest", "displayName": "Gemini 2.5 Flash Native Audio Latest", "description": "Latest release of Gemini 2.5 Flash Native Audio", "inputTokenLimit": 131072, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "countTokens", "bidiGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "countTokens", "bidiGenerateContent" ], "endpoints": [ { "name": "countTokens", "route": "POST /v1beta/models/gemini-2.5-flash-native-audio-latest:countTokens", "source": "live supportedGenerationMethods" }, { "name": "bidiGenerateContent", "route": "WSS /ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent (Live API)", "source": "live supportedGenerationMethods" } ], "tools": [], "pricing": "billed as the model the alias currently resolves to (see aliases)", "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "live version field holds the display name ('Gemini 2.5 Flash Native Audio Latest') instead of a version", "live-listed id without a dedicated docs model page" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "alias_policy": "hot-swapped with every new release of the variation; 2-week e-mail notice before breaking changes (models.md)", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.5-flash-native-audio-preview-09-2025", "display_name": "Gemini 2.5 Flash Native Audio Preview 09-2025", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 2.5", "generation": "2.5", "description": "Gemini 2.5 Flash Native Audio Preview 09-2025", "status": [ "LIVE_DISCOVERED", "PREVIEW" ], "lifecycle_docs": "Preview", "release_date": null, "knowledge_cutoff": null, "context_window": 131072, "max_output": 8192, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": true, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": true, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemini-2.5-flash-native-audio-preview-09-2025", "version": "gemini-2.5-flash-preview-native-audio-dialog-2025-05-19", "displayName": "Gemini 2.5 Flash Native Audio Preview 09-2025", "description": "Gemini 2.5 Flash Native Audio Preview 09-2025", "inputTokenLimit": 131072, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "countTokens", "bidiGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "countTokens", "bidiGenerateContent" ], "endpoints": [ { "name": "countTokens", "route": "POST /v1beta/models/gemini-2.5-flash-native-audio-preview-09-2025:countTokens", "source": "live supportedGenerationMethods" }, { "name": "bidiGenerateContent", "route": "WSS /ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent (Live API)", "source": "live supportedGenerationMethods" } ], "tools": [], "pricing": "not listed on pricing.md; the 12-2025 preview is $0.50 text / $3.00 audio-video input, $2.00 text / $12.00 audio output per 1M tokens", "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "live-listed id without a dedicated docs model page" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.5-flash-native-audio-preview-12-2025", "display_name": "Gemini 2.5 Flash Native Audio Preview 12-2025", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 2.5", "generation": "2.5", "description": "Gemini 2.5 Flash Native Audio Preview 12-2025", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW" ], "lifecycle_docs": "Preview", "release_date": "2025-12-12", "knowledge_cutoff": "January 2025", "context_window": 131072, "max_output": 8192, "docs_input_token_limit": 131072, "docs_output_token_limit": 8192, "modalities": { "input": [ "text", "audio", "video" ], "output": [ "text", "audio" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": true, "video_input": true, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": true, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": true, "thought_signatures": false, "structured_output": false, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": false, "flex_inference": false, "priority_inference": false, "live_api": true, "tts": false, "audio_generation_docs": true, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemini-2.5-flash-native-audio-preview-12-2025", "version": "12-2025", "displayName": "Gemini 2.5 Flash Native Audio Preview 12-2025", "description": "Gemini 2.5 Flash Native Audio Preview 12-2025", "inputTokenLimit": 131072, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "countTokens", "bidiGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "countTokens", "bidiGenerateContent" ], "endpoints": [ { "name": "countTokens", "route": "POST /v1beta/models/gemini-2.5-flash-native-audio-preview-12-2025:countTokens", "source": "live supportedGenerationMethods" }, { "name": "bidiGenerateContent", "route": "WSS /ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent (Live API)", "source": "live supportedGenerationMethods" } ], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": { "currency": "USD", "input_text": 0.5, "input_audio_video": 3.0, "output_text": 2.0, "output_audio": 12.0, "unit": "per 1M tokens", "free_tier": "free of charge" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "free of charge", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-native-audio-preview-12-2025", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Preview: `gemini-2.5-flash-native-audio-preview-12-2025`", "docs_latest_update": "September 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3.1-flash-live-preview", "display_name": "Gemini 3.1 Flash Live Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 3.1", "generation": "3.1", "description": "Gemini 3.1 Flash Live Preview", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW" ], "lifecycle_docs": "Preview", "release_date": "2026-03-11", "knowledge_cutoff": "January 2025 (Gemini 3 model cards; not stated on the API model pages)", "context_window": 131072, "max_output": 65536, "docs_input_token_limit": 131072, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text", "audio" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": true, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": true, "structured_output": false, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": false, "flex_inference": "unknown", "priority_inference": "unknown", "live_api": true, "tts": false, "audio_generation_docs": true, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=2)", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemini-3.1-flash-live-preview", "version": "3.1-flash-live-03-2026", "displayName": "Gemini 3.1 Flash Live Preview", "description": "Gemini 3.1 Flash Live Preview", "inputTokenLimit": 131072, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "bidiGenerateContent" ], "thinking": null, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "bidiGenerateContent" ], "endpoints": [ { "name": "bidiGenerateContent", "route": "WSS /ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent (Live API)", "source": "live supportedGenerationMethods" } ], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": { "currency": "USD", "input_text": 0.75, "input_audio": 3.0, "input_audio_per_min": 0.005, "input_image_video": 1.0, "input_image_video_per_min": 0.002, "output_text": 4.5, "output_audio": 12.0, "output_audio_per_min": 0.018, "unit": "per 1M tokens", "free_tier": "free of charge", "grounding": "gemini3 (Google Search supported on free tier for these models)", "same_as": "gemini-3.8-live" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "free of charge", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "thinking: docs 'Supported' vs live thinking=None" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-live-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Preview: `gemini-3.1-flash-live-preview`", "model_card": "Model card", "docs_latest_update": "March 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3.8-live", "display_name": "Gemini 3.8 Live", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini 3.8", "generation": "3.8", "description": "Gemini 3.8 Live", "status": [ "DOCUMENTED", "LIVE_DISCOVERED" ], "lifecycle_docs": "Stable (GA)", "release_date": "2026-09-15", "knowledge_cutoff": "January 2025 (Gemini 3 model cards; not stated on the API model pages)", "context_window": 131072, "max_output": 65536, "docs_input_token_limit": 131072, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text", "audio" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": true, "video_output": false, "music_output": false, "embeddings": false, "thinking": "Supported (interleaved reasoning)", "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": true, "structured_output": false, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": false, "flex_inference": "unknown", "priority_inference": "unknown", "live_api": true, "tts": false, "audio_generation_docs": true, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=2)", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemini-3.8-live", "version": "3.1-flash-live-03-2026", "displayName": "Gemini 3.8 Live", "description": "Gemini 3.8 Live", "inputTokenLimit": 131072, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "bidiGenerateContent" ], "thinking": null, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "bidiGenerateContent" ], "endpoints": [ { "name": "bidiGenerateContent", "route": "WSS /ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent (Live API)", "source": "live supportedGenerationMethods" } ], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": { "currency": "USD", "input_text": 0.75, "input_audio": 3.0, "input_audio_per_min": 0.005, "input_image_video": 1.0, "input_image_video_per_min": 0.002, "output_text": 4.5, "output_audio": 12.0, "output_audio_per_min": 0.018, "unit": "per 1M tokens", "free_tier": "free of charge", "grounding": "gemini3 (Google Search supported on free tier for these models)" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "free of charge", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "thinking: docs 'Supported (interleaved reasoning)' vs live thinking=None", "live version field is '3.1-flash-live-03-2026' (same as gemini-3.1-flash-live-preview)", "docs: 'Thinking Supported (interleaved reasoning)' vs live thinking flag absent" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.8-live", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Stable: `gemini-3.8-live`", "model_card": "Model card", "docs_latest_update": "September 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3.8-live-extended-thinking", "display_name": "Gemini 3.8 Live Extended Thinking", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini 3.8", "generation": "3.8", "description": "Gemini 3.8 Live Extended Thinking", "status": [ "DOCUMENTED", "LIVE_DISCOVERED" ], "lifecycle_docs": "Stable (GA)", "release_date": "2026-09-15", "knowledge_cutoff": "January 2025 (Gemini 3 model cards; not stated on the API model pages)", "context_window": 131072, "max_output": 65536, "docs_input_token_limit": 131072, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text", "audio" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": true, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": true, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": true, "structured_output": false, "function_calling": "Supported (Async only)", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": true, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": false, "flex_inference": "unknown", "priority_inference": "unknown", "live_api": true, "tts": false, "audio_generation_docs": true, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=2)", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemini-3.8-live-extended-thinking", "version": "3.1-flash-live-03-2026", "displayName": "Gemini 3.8 Live Extended Thinking", "description": "Gemini 3.8 Live Extended Thinking", "inputTokenLimit": 131072, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "bidiGenerateContent" ], "thinking": true, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "bidiGenerateContent" ], "endpoints": [ { "name": "bidiGenerateContent", "route": "WSS /ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent (Live API)", "source": "live supportedGenerationMethods" } ], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": "Supported (Async only)" } ], "pricing": { "currency": "USD", "input_text": 0.75, "input_audio": 3.0, "input_audio_per_min": 0.005, "input_image_video": 1.0, "input_image_video_per_min": 0.002, "output_text": 4.5, "output_audio": 12.0, "output_audio_per_min": 0.018, "unit": "per 1M tokens", "free_tier": "free of charge", "grounding": "gemini3 (Google Search supported on free tier for these models)", "same_as": "gemini-3.8-live" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "free of charge", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "live version field is '3.1-flash-live-03-2026' (same as gemini-3.1-flash-live-preview)" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.8-live-extended-thinking", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Stable: `gemini-3.8-live-extended-thinking`", "model_card": "Model card", "docs_latest_update": "September 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-robotics-er-2-streaming-preview", "display_name": "Gemini Robotics-ER 2 Streaming Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini Robotics-ER", "generation": "2", "description": "Gemini Robotics-ER 2 Streaming Preview", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW" ], "lifecycle_docs": "Preview", "release_date": "2026-07-30", "knowledge_cutoff": "January 2025", "context_window": 131072, "max_output": 65536, "docs_input_token_limit": 131072, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": true, "url_context": true, "code_execution": true, "computer_use": true, "file_search": true, "context_caching_explicit": false, "context_caching_docs": true, "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": true, "flex_inference": false, "priority_inference": false, "live_api": true, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "live defaults temperature=1 topP=0.95 topK=64 maxTemperature=2", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemini-robotics-er-2-streaming-preview", "version": "2-streaming-preview", "displayName": "Gemini Robotics-ER 2 Streaming Preview", "description": "Gemini Robotics-ER 2 Streaming Preview", "inputTokenLimit": 131072, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "bidiGenerateContent" ], "thinking": null, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "bidiGenerateContent" ], "endpoints": [ { "name": "bidiGenerateContent", "route": "WSS /ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent (Live API)", "source": "live supportedGenerationMethods" } ], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "google_maps", "category": "server", "support": true }, { "type": "url_context", "category": "server", "support": true }, { "type": "code_execution", "category": "server", "support": true }, { "type": "computer_use", "category": "server", "support": true }, { "type": "file_search", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": "pricing.md section is empty ('Standard' heading without a table) as of 2026-09-18", "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "thinking: docs 'Supported' vs live thinking=None", "docs: Batch API supported, but batchGenerateContent absent from live supportedGenerationMethods", "docs: Caching supported, but createCachedContent absent from live supportedGenerationMethods" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-robotics-er-2-streaming-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Preview: `gemini-robotics-er-1.6-preview`", "model_card": "Model card", "docs_latest_update": "December 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-3.5-live-translate-preview", "display_name": "Gemini 3.5 Live Translate Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 3.5", "generation": "3.5", "description": "Gemini 3.5 Live Translate Preview", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "PREVIEW" ], "lifecycle_docs": "Preview", "release_date": "2026-06", "knowledge_cutoff": "January 2025 (Gemini 3 model cards; not stated on the API model pages)", "context_window": 16384, "max_output": 32768, "docs_input_token_limit": 131072, "docs_output_token_limit": 65536, "modalities": { "input": [ "audio" ], "output": [ "text", "audio" ] }, "thinking": "not supported", "capabilities": { "text_input": false, "image_input": false, "audio_input": true, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": true, "video_output": false, "music_output": false, "embeddings": false, "thinking": false, "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": false, "function_calling": false, "parallel_function_calling": false, "compositional_function_calling": false, "google_search_grounding": false, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": false, "flex_inference": false, "priority_inference": false, "live_api": true, "tts": false, "audio_generation_docs": true, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": true, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "deprecated since 2026-07-21 for Gemini 3.x (keep defaults; live Model.maxTemperature=2)", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/gemini-3.5-live-translate-preview", "version": "3.5-live-translate-06-2026", "displayName": "Gemini 3.5 Live Translate Preview", "description": "Gemini 3.5 Live Translate Preview", "inputTokenLimit": 16384, "outputTokenLimit": 32768, "supportedGenerationMethods": [ "bidiGenerateContent" ], "thinking": null, "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, "supportedGenerationMethods": [ "bidiGenerateContent" ], "endpoints": [ { "name": "bidiGenerateContent", "route": "WSS /ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent (Live API)", "source": "live supportedGenerationMethods" } ], "tools": [], "pricing": { "currency": "USD", "input_audio": 3.5, "input_audio_per_min": 0.0053, "output_audio": 21.0, "output_audio_per_min": 0.0315, "unit": "per 1M tokens", "note": "25 audio tokens/second; effective ~$0.0368 per minute", "free_tier": "free of charge" }, "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "free of charge", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [ "inputTokenLimit live=16384 vs docs=131072", "outputTokenLimit live=32768 vs docs=65536" ], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.5-live-translate-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Preview: `gemini-3.5-live-translate-preview`", "model_card": "Model card", "docs_latest_update": "June 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "lyria-realtime-exp", "display_name": "Lyria Realtime Experimental", "kind": "experimental", "aliases": [], "snapshots": [], "family": "Lyria", "generation": "realtime", "description": "Lyria Realtime Experimental", "status": [ "DOCUMENTED", "LIVE_DISCOVERED", "BETA" ], "lifecycle_docs": "Experimental", "release_date": "2025-05-20", "knowledge_cutoff": null, "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "audio (music, PCM stream)" ] }, "thinking": "not supported", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": false, "image_output": false, "audio_output": true, "video_output": false, "music_output": true, "embeddings": false, "thinking": false, "thinking_live_flag": null, "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": false, "thought_signatures": false, "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": false, "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": false, "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": true, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": false, "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "live defaults temperature=None topP=None topK=None maxTemperature=None", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": { "name": "models/lyria-realtime-exp", "version": "lyria-realtime-exp", "displayName": "Lyria Realtime Experimental", "description": "Lyria Realtime Experimental", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "bidiGenerateMusic" ], "thinking": null, "temperature": null, "topP": null, "topK": null, "maxTemperature": null }, "supportedGenerationMethods": [ "bidiGenerateMusic" ], "endpoints": [ { "name": "bidiGenerateMusic", "route": "WSS ...BidiGenerateMusic (Live Music API)", "source": "live supportedGenerationMethods" } ], "tools": [], "pricing": "not listed on pricing.md (experimental)", "rate_limits": { "documented": "Per-model RPM/TPM/RPD are shown only in AI Studio (https://aistudio.google.com/rate-limit); the docs page defines tiers Free/1/2/3, spend-based limits and batch limits.", "usage_tiers": { "Free": "active project; Pro models not available (observed limit 0)", "Tier 1": "billing linked; spend cap $250; spend rate limit $10/10 min", "Tier 2": "$100 paid + 3 days; $2,000 cap; $50/10 min", "Tier 3": "$1,000 paid + 30 days; $20,000-$100,000+ cap; $200/10 min" }, "priority_tier_multiplier": "0.3x the standard rate limit for the model/tier", "batch_enqueued_tokens": "not listed", "ref": "generated/fragments/rate-limits/gemini-rate-limits.json", "doc": "https://ai.google.dev/gemini-api/docs/rate-limits" }, "beta_headers": [], "restrictions": null, "availability": { "account": "listed for our key (GET /v1beta/models)", "api_versions": { "v1beta": true, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/lyria-realtime-exp", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Experimental: `lyria-realtime-exp`", "docs_latest_update": "May 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.0-flash", "display_name": "Gemini 2.0 Flash", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini 2.0", "generation": "2.0", "description": "**Warning:** Gemini 2.0 Flash is [deprecated] and has been shut down June 1, 2026. Migrate to [Gemini 3.5 Flash] to avoid service disruption.", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-02-05", "knowledge_cutoff": "August 2024", "context_window": 1048576, "max_output": 8192, "docs_input_token_limit": 1048576, "docs_output_token_limit": 8192, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "Experimental", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": false, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": true, "url_context": false, "code_execution": true, "computer_use": false, "file_search": false, "context_caching_explicit": true, "context_caching_docs": true, "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": true, "flex_inference": false, "priority_inference": false, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": [ 10000000, 1000000000, 5000000000 ] }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "google_maps", "category": "server", "support": true }, { "type": "code_execution", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-02-05", "earliest_shutdown": "2026-06-01", "replacement": "gemini-3.6-flash", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.0-flash", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - *Shut down* : `gemini-2.0-flash` - *Shut down* : `gemini-2.0-flash-001` - *Shut down* : `gemini-2.0-flash-exp`", "docs_latest_update": "February 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.0-flash-001", "display_name": "Gemini 2.0 Flash 001", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini 2.0", "generation": "2.0", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-02-05", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-02-05", "earliest_shutdown": "2026-06-01", "replacement": "gemini-3.6-flash", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.0-flash-lite", "display_name": "Gemini 2.0 Flash Lite", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini 2.0", "generation": "2.0", "description": "**Warning:** Gemini 2.0 Flash-Lite is [deprecated] and has been shut down June 1, 2026. Migrate to [Gemini 3.1 Flash-Lite] to avoid service disruption.", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-02-25", "knowledge_cutoff": "August 2024", "context_window": 1048576, "max_output": 8192, "docs_input_token_limit": 1048576, "docs_output_token_limit": 8192, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "thinking": "not supported", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": false, "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": false, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": false, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": true, "context_caching_docs": true, "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": true, "flex_inference": false, "priority_inference": false, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": [ 10000000, 1000000000, 5000000000 ] }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [ { "type": "function_declarations", "category": "client", "support": true } ], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-02-25", "earliest_shutdown": "2026-06-01", "replacement": "gemini-3.1-flash-lite", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.0-flash-lite", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - *Shut down* : `gemini-2.0-flash-lite` - *Shut down* : `gemini-2.0-flash-lite-001`", "docs_latest_update": "February 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.0-flash-lite-001", "display_name": "Gemini 2.0 Flash Lite 001", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini 2.0", "generation": "2.0", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-02-25", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-02-25", "earliest_shutdown": "2026-06-01", "replacement": "gemini-3.1-flash-lite", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.0-flash-exp", "display_name": "Gemini 2.0 Flash Exp", "kind": "experimental", "aliases": [], "snapshots": [], "family": "Gemini 2.0", "generation": "2.0", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "BETA", "UNVERIFIED" ], "lifecycle_docs": "Experimental", "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.0-flash-preview-image-generation", "display_name": "Gemini 2.0 Flash Preview Image Generation", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 2.0", "generation": "2.0", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-05-07", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-05-07", "earliest_shutdown": "2025-11-14", "replacement": "gemini-2.5-flash-image", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.0-flash-lite-preview", "display_name": "Gemini 2.0 Flash Lite Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 2.0", "generation": "2.0", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-02-05", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-02-05", "earliest_shutdown": "2025-12-09", "replacement": "gemini-2.5-flash-lite", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.0-flash-lite-preview-02-05", "display_name": "Gemini 2.0 Flash Lite Preview 02 05", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 2.0", "generation": "2.0", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-02-05", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-02-05", "earliest_shutdown": "2025-12-09", "replacement": "gemini-2.5-flash-lite", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.0-flash-live-001", "display_name": "Gemini 2.0 Flash Live 001", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini 2.0", "generation": "2.0", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-04-09", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-04-09", "earliest_shutdown": "2025-12-09", "replacement": "gemini-3.8-live", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.5-pro-preview-03-25", "display_name": "Gemini 2.5 Pro Preview 03 25", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 2.5", "generation": "2.5", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-03-03", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-03-03", "earliest_shutdown": "2025-12-02", "replacement": "gemini-3.1-pro-preview", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.5-pro-preview-05-06", "display_name": "Gemini 2.5 Pro Preview 05 06", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 2.5", "generation": "2.5", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-05-06", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-05-06", "earliest_shutdown": "2025-12-02", "replacement": "gemini-3.1-pro-preview", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.5-pro-preview-06-05", "display_name": "Gemini 2.5 Pro Preview 06 05", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 2.5", "generation": "2.5", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-06-05", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-06-05", "earliest_shutdown": "2025-12-02", "replacement": "gemini-3.1-pro-preview", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.5-flash-preview-05-20", "display_name": "Gemini 2.5 Flash Preview 05 20", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 2.5", "generation": "2.5", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-05-20", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-05-20", "earliest_shutdown": "2025-11-18", "replacement": "gemini-3.6-flash", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.5-flash-preview-09-2025", "display_name": "Gemini 2.5 Flash Preview 09 2025", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 2.5", "generation": "2.5", "description": "This model is [shut down] as of February 17, 2026; migrate to [Gemini 2.5 Flash] for improved performance.", "status": [ "DOCUMENTED", "PREVIEW", "UNVERIFIED" ], "lifecycle_docs": "Preview", "release_date": null, "knowledge_cutoff": "January 2025", "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": 1048576, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": false, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": false, "url_context": true, "code_execution": true, "computer_use": false, "file_search": true, "context_caching_explicit": true, "context_caching_docs": true, "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": true, "flex_inference": false, "priority_inference": false, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "url_context", "category": "server", "support": true }, { "type": "code_execution", "category": "server", "support": true }, { "type": "file_search", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-preview-09-2025", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Stable: `gemini-2.5-flash` - Shut down: `gemini-2.5-flash-preview-09-2025`", "docs_latest_update": "September 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.5-flash-preview-09-25", "display_name": "Gemini 2.5 Flash Preview 09 25", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 2.5", "generation": "2.5", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-09-25", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-09-25", "earliest_shutdown": "2026-02-17", "replacement": "gemini-3.6-flash", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.5-flash-lite-preview-09-2025", "display_name": "Gemini 2.5 Flash Lite Preview 09 2025", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 2.5", "generation": "2.5", "description": "This model is [shut down] as of March 31, 2026. Migrate to [Gemini 3.1 Flash-Lite] to avoid service disruption.", "status": [ "DOCUMENTED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-09-25", "knowledge_cutoff": "January 2025", "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": 1048576, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": true, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": false, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": false, "url_context": true, "code_execution": true, "computer_use": false, "file_search": true, "context_caching_explicit": true, "context_caching_docs": true, "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": true, "flex_inference": false, "priority_inference": false, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "url_context", "category": "server", "support": true }, { "type": "code_execution", "category": "server", "support": true }, { "type": "file_search", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-09-25", "earliest_shutdown": "2026-03-31", "replacement": "gemini-3.1-flash-lite", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-lite-preview-09-2025", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Stable: `gemini-2.5-flash-lite` - Shut down: `gemini-2.5-flash-lite-preview-09-2025`", "docs_latest_update": "September 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-2.5-flash-image-preview", "display_name": "Gemini 2.5 Flash Image Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini 2.5", "generation": "2.5", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-05-07", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-05-07", "earliest_shutdown": "2026-01-15", "replacement": "gemini-2.5-flash-image", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-live-2.5-flash-preview", "display_name": "Gemini Live 2.5 Flash Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini", "generation": null, "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-06-17", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-06-17", "earliest_shutdown": "2025-12-09", "replacement": "gemini-3.8-live", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "text-embedding-004", "display_name": "Text Embedding 004", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini Embedding", "generation": null, "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2024-04-09", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed", "embedding_dimensions": "flexible 128-3072 (recommended 768, 1536, 3072; default 3072, MRL truncation; embedding-2 auto-renormalizes)", "embedding_task_type_param": false, "embedding_input_token_limit": 8192 }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2024-04-09", "earliest_shutdown": "2026-01-14", "replacement": "gemini-embedding-2", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "embedding-001", "display_name": "Embedding 001", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini Embedding", "generation": null, "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2024-04-09", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed", "embedding_dimensions": "flexible 128-3072 (recommended 768, 1536, 3072; default 3072, MRL truncation; embedding-2 auto-renormalizes)", "embedding_task_type_param": false, "embedding_input_token_limit": 8192 }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2024-04-09", "earliest_shutdown": "2025-10-30", "replacement": "gemini-embedding-2", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "embedding-gecko-001", "display_name": "Embedding Gecko 001", "kind": "stable", "aliases": [], "snapshots": [], "family": "Gemini Embedding", "generation": null, "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed", "embedding_dimensions": "flexible 128-3072 (recommended 768, 1536, 3072; default 3072, MRL truncation; embedding-2 auto-renormalizes)", "embedding_task_type_param": false, "embedding_input_token_limit": 8192 }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": null, "earliest_shutdown": "2025-10-30", "replacement": "gemini-embedding-2", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-embedding-exp", "display_name": "Gemini Embedding Exp", "kind": "experimental", "aliases": [], "snapshots": [], "family": "Gemini Embedding", "generation": "gemini-embedding-exp", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "BETA", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed", "embedding_dimensions": "flexible 128-3072 (recommended 768, 1536, 3072; default 3072, MRL truncation; embedding-2 auto-renormalizes)", "embedding_task_type_param": false, "embedding_input_token_limit": 8192 }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": null, "earliest_shutdown": "2025-10-30", "replacement": "gemini-embedding-2", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-embedding-exp-03-07", "display_name": "Gemini Embedding Exp 03 07", "kind": "experimental", "aliases": [], "snapshots": [], "family": "Gemini Embedding", "generation": "gemini-embedding-exp-03-07", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "BETA", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed", "embedding_dimensions": "flexible 128-3072 (recommended 768, 1536, 3072; default 3072, MRL truncation; embedding-2 auto-renormalizes)", "embedding_task_type_param": false, "embedding_input_token_limit": 8192 }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": null, "earliest_shutdown": "2025-10-30", "replacement": "gemini-embedding-2", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "embedding-2-preview", "display_name": "Embedding 2 Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini Embedding", "generation": null, "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2026-03-10", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed", "embedding_dimensions": "flexible 128-3072 (recommended 768, 1536, 3072; default 3072, MRL truncation; embedding-2 auto-renormalizes)", "embedding_task_type_param": false, "embedding_input_token_limit": 8192 }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2026-03-10", "earliest_shutdown": "2026-08-10", "replacement": "gemini-embedding-2", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "imagen-4.0-generate-001", "display_name": "Imagen", "kind": "stable", "aliases": [], "snapshots": [], "family": "Imagen", "generation": "4.0", "description": "The Imagen 4 standard, ultra, and fast endpoints are [deprecated] and will be shut down on \\*\\*August 17, 2026\\*\\*; migrate to [Gemini 3.1 Flash Image] to avoid service interruptions.", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-06-24", "knowledge_cutoff": null, "context_window": 480, "max_output": null, "docs_input_token_limit": 480, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": false, "image_output": true, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": false, "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": true, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-06-24", "earliest_shutdown": "2026-08-17", "replacement": "gemini-3.1-flash-image", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "live_api", "verified_at": "2026-09-19T00:00:00Z", "result": "failure", "http_status": 404, "request_note": "GET /v1beta/models/imagen-4.0-generate-001 -> 404", "error_body": { "error": { "code": 404, "message": "Model is not found: models/imagen-4.0-generate-001 for api version v1beta", "status": "NOT_FOUND" } } }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/imagen", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_latest_update": "June 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "imagen-4.0-ultra-generate-001", "display_name": "Imagen", "kind": "stable", "aliases": [], "snapshots": [], "family": "Imagen", "generation": "4.0", "description": "The Imagen 4 standard, ultra, and fast endpoints are [deprecated] and will be shut down on \\*\\*August 17, 2026\\*\\*; migrate to [Gemini 3.1 Flash Image] to avoid service interruptions.", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-06-24", "knowledge_cutoff": null, "context_window": 480, "max_output": null, "docs_input_token_limit": 480, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": false, "image_output": true, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": false, "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": true, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-06-24", "earliest_shutdown": "2026-08-17", "replacement": "gemini-3.1-flash-image", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/imagen", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_latest_update": "June 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "imagen-4.0-fast-generate-001", "display_name": "Imagen", "kind": "stable", "aliases": [], "snapshots": [], "family": "Imagen", "generation": "4.0", "description": "The Imagen 4 standard, ultra, and fast endpoints are [deprecated] and will be shut down on \\*\\*August 17, 2026\\*\\*; migrate to [Gemini 3.1 Flash Image] to avoid service interruptions.", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-06-24", "knowledge_cutoff": null, "context_window": 480, "max_output": null, "docs_input_token_limit": 480, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": false, "image_output": true, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": false, "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": true, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-06-24", "earliest_shutdown": "2026-08-17", "replacement": "gemini-3.1-flash-image", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/imagen", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_latest_update": "June 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "imagen-3.0-generate-002", "display_name": "Imagen 3.0 Generate 002", "kind": "stable", "aliases": [], "snapshots": [], "family": "Imagen", "generation": "3.0", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-02-06", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-02-06", "earliest_shutdown": "2025-11-10", "replacement": "imagen-4.0-generate-001", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "imagen-4.0-generate-preview-06-06", "display_name": "Imagen 4.0 Generate Preview 06 06", "kind": "preview", "aliases": [], "snapshots": [], "family": "Imagen", "generation": "4.0", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-06-24", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-06-24", "earliest_shutdown": "2026-02-17", "replacement": "imagen-4.0-generate-001", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "imagen-4.0-ultra-generate-preview-06-06", "display_name": "Imagen 4.0 Ultra Generate Preview 06 06", "kind": "preview", "aliases": [], "snapshots": [], "family": "Imagen", "generation": "4.0", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-06-24", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-06-24", "earliest_shutdown": "2026-02-17", "replacement": "imagen-4.0-ultra-generate-001", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "veo-2.0-generate-001", "display_name": "Veo 2.0 Generate 001", "kind": "stable", "aliases": [], "snapshots": [], "family": "Veo", "generation": "2.0", "description": "This model was [shut down] on \\*\\*June 30, 2026\\*\\*; migrate to [Veo 3.1 Preview] or the GA models available through the [Gemini Enterprise Agent Platform] to avoid service interruptions.", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-04-09", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text", "image" ], "output": [ "video" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": false, "image_output": false, "audio_output": false, "video_output": true, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": false, "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": true, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-04-09", "earliest_shutdown": "2026-06-30", "replacement": "veo-3.1-generate-preview", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/veo-2.0-generate-001", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_latest_update": "April 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "veo-3.0-generate-001", "display_name": "Veo 3.0 Generate 001", "kind": "stable", "aliases": [], "snapshots": [], "family": "Veo", "generation": "3.0", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-09-09", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-09-09", "earliest_shutdown": "2026-06-30", "replacement": "veo-3.1-generate-preview", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "veo-3.0-fast-generate-001", "display_name": "Veo 3.0 Fast Generate 001", "kind": "stable", "aliases": [], "snapshots": [], "family": "Veo", "generation": "3.0", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-09-09", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-09-09", "earliest_shutdown": "2026-06-30", "replacement": "veo-3.1-fast-generate-preview", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "veo-3.0-generate-preview", "display_name": "Veo 3.0 Generate Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Veo", "generation": "3.0", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-07-31", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-07-31", "earliest_shutdown": "2025-11-12", "replacement": "veo-3.1-generate-preview", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "veo-3.0-fast-generate-preview", "display_name": "Veo 3.0 Fast Generate Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Veo", "generation": "3.0", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-07-31", "knowledge_cutoff": null, "context_window": null, "max_output": null, "docs_input_token_limit": null, "docs_output_token_limit": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": false, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": "unknown", "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": "unknown", "structured_output": "unknown", "function_calling": "unknown", "parallel_function_calling": "unknown", "compositional_function_calling": "unknown", "google_search_grounding": "unknown", "google_maps_grounding": "unknown", "url_context": "unknown", "code_execution": "unknown", "computer_use": "unknown", "file_search": "unknown", "context_caching_explicit": "unknown", "context_caching_docs": "unknown", "context_caching_implicit": "unknown", "batch_api": "unknown", "batch_api_docs": "unknown", "flex_inference": "unknown", "priority_inference": "unknown", "live_api": "unknown", "tts": false, "audio_generation_docs": "unknown", "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-07-31", "earliest_shutdown": "2025-11-12", "replacement": "veo-3.1-fast-generate-preview", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-robotics-er-1.5-preview", "display_name": "Gemini Robotics Er 1.5 Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini Robotics-ER", "generation": "1.5", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2025-09-25", "knowledge_cutoff": "January 2025", "context_window": 1048576, "max_output": 65536, "docs_input_token_limit": 1048576, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": false, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": false, "url_context": true, "code_execution": true, "computer_use": false, "file_search": "unknown", "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": false, "flex_inference": false, "priority_inference": false, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "url_context", "category": "server", "support": true }, { "type": "code_execution", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2025-09-25", "earliest_shutdown": "2026-04-30", "replacement": "gemini-robotics-er-1.6-preview", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-robotics-er-1.5-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Preview: `gemini-robotics-er-1.5-preview`", "docs_latest_update": "September 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "gemini-robotics-er-1.6-preview", "display_name": "Gemini Robotics Er 1.6 Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Gemini Robotics-ER", "generation": "1.6", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "PREVIEW", "RETIRED" ], "lifecycle_docs": "Shut down", "release_date": "2026-04-14", "knowledge_cutoff": "January 2025", "context_window": 131072, "max_output": 65536, "docs_input_token_limit": 131072, "docs_output_token_limit": 65536, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "thinking": "unknown", "capabilities": { "text_input": true, "image_input": true, "audio_input": true, "video_input": true, "pdf_input": false, "text_output": true, "image_output": false, "audio_output": false, "video_output": false, "music_output": false, "embeddings": false, "thinking": true, "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": false, "structured_output": true, "function_calling": true, "parallel_function_calling": true, "compositional_function_calling": true, "google_search_grounding": true, "google_maps_grounding": true, "url_context": true, "code_execution": true, "computer_use": true, "file_search": true, "context_caching_explicit": true, "context_caching_docs": true, "context_caching_implicit": "unknown", "batch_api": true, "batch_api_docs": true, "flex_inference": true, "priority_inference": true, "live_api": false, "tts": false, "audio_generation_docs": false, "image_generation": false, "video_generation": false, "music_generation": false, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [], "tools": [ { "type": "google_search", "category": "server", "support": true }, { "type": "google_maps", "category": "server", "support": true }, { "type": "url_context", "category": "server", "support": true }, { "type": "code_execution", "category": "server", "support": true }, { "type": "computer_use", "category": "server", "support": true }, { "type": "file_search", "category": "server", "support": true }, { "type": "function_declarations", "category": "client", "support": true } ], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": { "announced_release": "2026-04-14", "earliest_shutdown": "2026-08-31", "replacement": "gemini-robotics-er-2-preview", "source": "https://ai.google.dev/gemini-api/docs/deprecations" }, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-robotics-er-1.6-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/thinking", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Preview: `gemini-robotics-er-1.6-preview`", "docs_latest_update": "December 2025", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "lyria-3.5-clip-preview", "display_name": "Lyria 3.5 Clip Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Lyria", "generation": "3.5", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "PREVIEW", "UNVERIFIED" ], "lifecycle_docs": "Preview", "release_date": null, "knowledge_cutoff": null, "context_window": 131072, "max_output": null, "docs_input_token_limit": 131072, "docs_output_token_limit": null, "modalities": { "input": [ "text", "image" ], "output": [ "audio (music)", "text (lyrics)" ] }, "thinking": "not supported", "capabilities": { "text_input": true, "image_input": true, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": false, "image_output": false, "audio_output": true, "video_output": false, "music_output": true, "embeddings": false, "thinking": false, "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": false, "structured_output": false, "function_calling": false, "parallel_function_calling": false, "compositional_function_calling": false, "google_search_grounding": false, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": false, "flex_inference": false, "priority_inference": false, "live_api": false, "tts": false, "audio_generation_docs": true, "image_generation": false, "video_generation": false, "music_generation": true, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [ { "name": "interactions", "route": "POST /v1beta/interactions (model=lyria-3.5-clip-preview)", "source": "docs (music-generation.md / omni.md use the Interactions API)" } ], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/lyria-3.5-clip-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Preview: `lyria-3.5-clip-preview` - Preview: `lyria-3.5-pro-preview`", "docs_latest_update": "September 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "gemini", "id": "lyria-3.5-pro-preview", "display_name": "Lyria 3.5 Pro Preview", "kind": "preview", "aliases": [], "snapshots": [], "family": "Lyria", "generation": "3.5", "description": "documented model (see deprecations)", "status": [ "DOCUMENTED", "PREVIEW", "UNVERIFIED" ], "lifecycle_docs": "Preview", "release_date": null, "knowledge_cutoff": null, "context_window": 131072, "max_output": null, "docs_input_token_limit": 131072, "docs_output_token_limit": null, "modalities": { "input": [ "text", "image" ], "output": [ "audio (music)", "text (lyrics)" ] }, "thinking": "not supported", "capabilities": { "text_input": true, "image_input": true, "audio_input": false, "video_input": false, "pdf_input": false, "text_output": false, "image_output": false, "audio_output": true, "video_output": false, "music_output": true, "embeddings": false, "thinking": false, "thinking_live_flag": "n/a", "thinking_default_level": "unknown", "thinking_levels": "unknown", "thinking_level_param": false, "thinking_budget_legacy_param": "unknown", "thought_signatures": false, "structured_output": false, "function_calling": false, "parallel_function_calling": false, "compositional_function_calling": false, "google_search_grounding": false, "google_maps_grounding": false, "url_context": false, "code_execution": false, "computer_use": false, "file_search": false, "context_caching_explicit": false, "context_caching_docs": false, "context_caching_implicit": "unknown", "batch_api": false, "batch_api_docs": false, "flex_inference": false, "priority_inference": false, "live_api": false, "tts": false, "audio_generation_docs": true, "image_generation": false, "video_generation": false, "music_generation": true, "transcription_dedicated": false, "live_translation": false, "speaker_diarization": "n/a", "tuning": false, "tuning_note": "Fine-tuning is no longer offered on the Gemini Developer API (model-tuning.md); use Gemini Enterprise Agent Platform supervised tuning", "interactions_api": false, "interactions_api_listed_in_docs_table": false, "deep_research_agent": false, "managed_agent": false, "openai_compatible_chat": "unknown", "openai_compatible_embeddings": false, "openai_compatible_images_generations": false, "openai_compatible_videos": false, "system_instructions": false, "sampling_params_temperature_top_p_top_k": "unknown", "batch_enqueued_tokens_tier1_tier2_tier3": "not listed" }, "live_model_metadata": null, "supportedGenerationMethods": null, "endpoints": [ { "name": "interactions", "route": "POST /v1beta/interactions (model=lyria-3.5-pro-preview)", "source": "docs (music-generation.md / omni.md use the Interactions API)" } ], "tools": [], "pricing": "retired / not priced", "rate_limits": { "ref": "generated/fragments/rate-limits/gemini-rate-limits.json" }, "beta_headers": [], "restrictions": null, "availability": { "account": "not listed for our key", "api_versions": { "v1beta": false, "v1": false, "note": "docs (api-versions.md) say all models are in both versions; live GET /v1/models lists only 22 GA ids and GET /v1/models/gemini-3.1-pro-preview -> 404 'for api version v1'" }, "free_tier": "see pricing", "regions": "Gemini API / AI Studio available in ~190 countries and territories (available-regions.md); EEA/UK/CH: free & paid tiers available, but API clients offered to EEA/CH/UK end users must use Paid Services (terms)", "platforms": [ "Gemini Developer API (generativelanguage.googleapis.com)", "Google AI Studio", "Gemini Enterprise Agent Platform (Vertex AI) for most Gemini/Veo/Imagen ids - not verified here" ] }, "deprecation": null, "discrepancies_live_vs_docs": [], "last_verified": "2026-09-19", "verification": { "method": "docs_only", "verified_at": "2026-09-19T00:00:00Z", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/models", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/api/models", "retrieved_at": "2026-09-18", "note": "GET /v1beta/models live listing 2026-09-19" }, { "url": "https://ai.google.dev/gemini-api/docs/models/lyria-3.5-pro-preview", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://ai.google.dev/gemini-api/docs/rate-limits", "retrieved_at": "2026-09-18" } ], "docs_versions": "Read the model version patterns for more details. - Preview: `lyria-3.5-clip-preview` - Preview: `lyria-3.5-pro-preview`", "docs_latest_update": "September 2026", "_fragment": "generated/fragments/models/gemini-models.json" }, { "provider": "openai", "id": "ada", "record_kind": "id_only", "canonical_model": "ada", "display_name": "ada", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "legacy-retired", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`babbage-002`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" }, { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`babbage-002`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "babbage", "record_kind": "id_only", "canonical_model": "babbage", "display_name": "babbage", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "legacy-retired", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`babbage-002`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" }, { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`babbage-002`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "babbage-002", "record_kind": "model", "canonical_model": "babbage-002", "display_name": "babbage-002", "description": "Replacement for the GPT-3 ada and babbage base models", "aliases": [], "snapshots": [], "default_snapshot": "babbage-002", "family": "base-legacy", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED", "LEGACY" ], "flags": [], "release_date": "2023-08-21", "release_date_source": "GET /v1/models created timestamp (approximation)", "knowledge_cutoff": "2021-09-01", "context_window": null, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": true, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Completions (legacy)", "route": "/v1/completions" } ], "tools": [], "features_documented": [ "fine_tuning" ], "pricing": { "standard": { "input": 0.4, "_unit": "per 1M tokens", "output": 0.4, "fine_tuning_training": 0.4, "fine_tuned_input": 1.6, "fine_tuned_output": 1.6 }, "batch": { "input": 0.2, "_unit": "per 1M tokens", "output": 0.2, "fine_tuning_training": 0.4, "fine_tuned_input": 0.8, "fine_tuned_output": 0.9 }, "model_page:Text tokens": { "Input": { "price": 0.4, "unit": "1M tokens" }, "Output": { "price": 0.4, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 10000, "Batch queue limit": 100000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 40000, "Batch queue limit": 200000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 80000, "Batch queue limit": 5000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 300000, "Batch queue limit": 30000000 }, "Tier 5": { "RPM": 10000, "RPD": null, "TPM": 1000000, "Batch queue limit": 150000000 } } } }, "source": "https://developers.openai.com/api/docs/models/babbage-002", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1692634615, "openapi_enum": true }, "deprecation": [ { "announced": "2025-09-26", "shutdown_date": "2026-09-28", "replacement": "`gpt-5.6-terra`", "phase": "upcoming", "section": "2025-09-26: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2025-09-26-legacy-gpt-model-snapshots" }, { "announced": "2024-08-29", "shutdown_date": "2024-10-28", "replacement": "`gpt-4o-mini`", "phase": "past", "section": "2024-08-29: Fine-tuning training on babbage-002 and davinci-002 models", "source": "https://developers.openai.com/api/docs/deprecations#2024-08-29-fine-tuning-training-on-babbage-002-and-davinci-002-models" }, { "announced": null, "shutdown_date": "2026-09-28", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-09-28", "intro": "GPT base models can understand and generate natural language or code but are not trained with instruction following. These models are made to be replacements for our original GPT-3 base models and use the legacy Completions API. Most customers should use GPT-3.5 or GPT-4.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/babbage-002", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-09-26-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2024-08-29-fine-tuning-training-on-babbage-002-and-davinci-002-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "chat-latest", "record_kind": "model", "canonical_model": "chat-latest", "display_name": "Chat Latest", "description": "Latest Instant model used in ChatGPT", "aliases": [], "snapshots": [], "default_snapshot": "chat-latest", "family": "chatgpt-latest", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-05-05", "release_date_source": "changelog", "knowledge_cutoff": "2025-08-31", "context_window": 400000, "max_input": 272000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "function_calling", "image_input", "streaming", "structured_outputs" ], "pricing": { "standard": { "input": 5.0, "_unit": "per 1M tokens", "cached_input": 0.5, "output": 30.0 }, "model_page:Text tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Cached input": { "price": 0.5, "unit": "1M tokens" }, "Output": { "price": 30.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 50000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/chat-latest", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1777704602, "openapi_enum": false }, "deprecation": [], "shutdown_date": null, "intro": "chat-latest points to the latest Instant model currently used in ChatGPT. We recommend leveraging [GPT-6 Astra](/api/docs/models/gpt-6-astra) for production API usage. Learn more on the [Model guidance](/api/docs/guides/latest-model) page. The underlying model snapshot will be regularly updated.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/chat-latest", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "chatgpt-4o-latest", "record_kind": "model", "canonical_model": "chatgpt-4o-latest", "display_name": "ChatGPT-4o", "description": "GPT-4o model used in ChatGPT", "aliases": [], "snapshots": [], "default_snapshot": "chatgpt-4o-latest", "family": "chatgpt-latest", "status": [ "DOCUMENTED", "RETIRED", "LEGACY" ], "flags": [], "release_date": "2024-08-15", "release_date_source": "changelog", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": true, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": "unknown", "tool_file_search": "unknown", "tool_code_interpreter": "unknown", "tool_image_generation": "unknown", "tool_mcp": "unknown", "tool_computer_use": "unknown", "tool_hosted_shell": "unknown", "tool_apply_patch": "unknown", "tool_skills": "unknown", "tool_tool_search": "unknown", "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" } ], "tools": [], "features_documented": [ "image_input", "predicted_outputs", "streaming" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Output": { "price": 15.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/chatgpt-4o-latest", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2025-11-18", "shutdown_date": "2026-02-17", "replacement": "`gpt-5.1-chat-latest`", "phase": "past", "section": "2025-11-18: `chatgpt-4o-latest` snapshot", "source": "https://developers.openai.com/api/docs/deprecations#2025-11-18-chatgpt-4o-latest-snapshot" } ], "shutdown_date": "2026-02-17", "intro": "ChatGPT-4o was a model alias for the GPT-4o snapshot used in ChatGPT. It has been deprecated and removed from the API. We recommend using [GPT-6 Astra](/api/docs/models/gpt-6-astra) for most API integrations.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "failure", "http_status": 404, "request_note": "GET /v1/models/chatgpt-4o-latest -> 404 (a 404 with our key never means the model does not exist)", "get_model": { "status": 404, "error_type": "invalid_request_error", "error_code": "model_not_found", "error_message": "The model 'chatgpt-4o-latest' does not exist" } }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/chatgpt-4o-latest", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-11-18-chatgpt-4o-latest-snapshot", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "chatgpt-image-latest", "record_kind": "model", "canonical_model": "chatgpt-image-latest", "display_name": "chatgpt-image-latest", "description": "Previous image model used in ChatGPT.", "aliases": [], "snapshots": [], "default_snapshot": "chatgpt-image-latest", "family": "image", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-12-16", "release_date_source": "changelog", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "image", "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": true, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": true, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": true, "image_edit_api": true, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Batch", "route": "/v1/batch" }, { "name": "Image generation", "route": "/v1/images/generations" }, { "name": "Image edit", "route": "/v1/images/edits" } ], "tools": [], "features_documented": [ "inpainting" ], "pricing": { "standard": { "image_input": 8.0, "_unit": "per 1M tokens", "image_cached_input": 2.0, "image_output": 32.0, "text_input": 5.0, "text_cached_input": 1.25, "text_output": 10.0 }, "batch": { "image_input": 4.0, "_unit": "per 1M tokens", "image_cached_input": 1.0, "image_output": 16.0, "text_input": 2.5, "text_cached_input": 0.63, "text_output": 5.0 }, "model_page:Text tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Cached input": { "price": 1.25, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } }, "model_page:Image tokens": { "Input": { "price": 8.0, "unit": "1M tokens" }, "Cached input": { "price": 2.0, "unit": "1M tokens" }, "Output": { "price": 32.0, "unit": "1M tokens" } }, "model_page:Image generation": { "1024x1024": { "price": 0.133, "unit": "image" }, "1024x1536": { "price": 0.2, "unit": "image" }, "1536x1024": { "price": 0.2, "unit": "image" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "TPM", "IPM" ], "note": null, "tiers": { "Tier 1": { "TPM": 100000, "IPM": 5 }, "Tier 2": { "TPM": 250000, "IPM": 20 }, "Tier 3": { "TPM": 800000, "IPM": 50 }, "Tier 4": { "TPM": 3000000, "IPM": 150 }, "Tier 5": { "TPM": 8000000, "IPM": 250 } } } }, "source": "https://developers.openai.com/api/docs/models/chatgpt-image-latest", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1765925279, "openapi_enum": true }, "deprecation": [ { "announced": "2026-06-02", "shutdown_date": "2026-12-01", "replacement": "`gpt-image-2`", "phase": "upcoming", "section": "2026-06-02: GPT Image model deprecations", "source": "https://developers.openai.com/api/docs/deprecations#2026-06-02-gpt-image-model-deprecations" }, { "announced": null, "shutdown_date": "2026-12-01", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-12-01", "intro": "This points to the Image snapshot previously used in ChatGPT. We recommend [GPT-Image-2.5 Sunburst](/api/docs/models/gpt-image-2.5-sunburst) for API use.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/chatgpt-image-latest", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-06-02-gpt-image-model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "code-cushman-001", "record_kind": "id_only", "canonical_model": "code-cushman-001", "display_name": "code-cushman-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "legacy-retired", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-03-20", "shutdown_date": "2023-03-23", "replacement": "`gpt-4o`", "phase": "past", "section": "2023-03-20: Codex models", "source": "https://developers.openai.com/api/docs/deprecations#2023-03-20-codex-models" } ], "shutdown_date": "2023-03-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-03-20-codex-models", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "code-cushman-002", "record_kind": "id_only", "canonical_model": "code-cushman-002", "display_name": "code-cushman-002", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "legacy-retired", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-03-20", "shutdown_date": "2023-03-23", "replacement": "`gpt-4o`", "phase": "past", "section": "2023-03-20: Codex models", "source": "https://developers.openai.com/api/docs/deprecations#2023-03-20-codex-models" } ], "shutdown_date": "2023-03-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-03-20-codex-models", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "code-davinci-001", "record_kind": "id_only", "canonical_model": "code-davinci-001", "display_name": "code-davinci-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "legacy-retired", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-03-20", "shutdown_date": "2023-03-23", "replacement": "`gpt-4o`", "phase": "past", "section": "2023-03-20: Codex models", "source": "https://developers.openai.com/api/docs/deprecations#2023-03-20-codex-models" } ], "shutdown_date": "2023-03-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-03-20-codex-models", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "code-davinci-002", "record_kind": "id_only", "canonical_model": "code-davinci-002", "display_name": "code-davinci-002", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "legacy-retired", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`gpt-3.5-turbo-instruct`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" }, { "announced": "2023-03-20", "shutdown_date": "2023-03-23", "replacement": "`gpt-4o`", "phase": "past", "section": "2023-03-20: Codex models", "source": "https://developers.openai.com/api/docs/deprecations#2023-03-20-codex-models" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2023-03-20-codex-models", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "code-davinci-edit-001", "record_kind": "id_only", "canonical_model": "code-davinci-edit-001", "display_name": "code-davinci-edit-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "legacy-retired", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`gpt-4o`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "code-search-ada-code-001", "record_kind": "id_only", "canonical_model": "code-search-ada-code-001", "display_name": "code-search-ada-code-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "embeddings", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`text-embedding-3-small`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "code-search-ada-text-001", "record_kind": "id_only", "canonical_model": "code-search-ada-text-001", "display_name": "code-search-ada-text-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "embeddings", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`text-embedding-3-small`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "code-search-babbage-code-001", "record_kind": "id_only", "canonical_model": "code-search-babbage-code-001", "display_name": "code-search-babbage-code-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "embeddings", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`text-embedding-3-small`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "code-search-babbage-text-001", "record_kind": "id_only", "canonical_model": "code-search-babbage-text-001", "display_name": "code-search-babbage-text-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "embeddings", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`text-embedding-3-small`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "codex-mini-latest", "record_kind": "model", "canonical_model": "codex-mini-latest", "display_name": "codex-mini-latest", "description": "Fast reasoning model optimized for the Codex CLI", "aliases": [], "snapshots": [], "default_snapshot": "codex-mini-latest", "family": "codex", "status": [ "DOCUMENTED", "RETIRED" ], "flags": [], "release_date": "2025-05-15", "release_date_source": "changelog", "knowledge_cutoff": "2024-06-01", "context_window": 200000, "max_input": null, "max_output": 100000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": true, "stored_completions": true, "distillation": true, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": "unknown", "tool_file_search": "unknown", "tool_code_interpreter": "unknown", "tool_image_generation": "unknown", "tool_mcp": "unknown", "tool_computer_use": "unknown", "tool_hosted_shell": "unknown", "tool_apply_patch": "unknown", "tool_skills": "unknown", "tool_tool_search": "unknown", "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" } ], "tools": [], "features_documented": [ "evals", "function_calling", "image_input", "prompt_caching", "stored_completions", "streaming", "structured_outputs" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 1.5, "unit": "1M tokens" }, "Cached input": { "price": 0.375, "unit": "1M tokens" }, "Output": { "price": 6.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 1000, "TPM": 100000, "Batch queue limit": 1000000 }, "Tier 2": { "RPM": 2000, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 3": { "RPM": 5000, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "TPM": 150000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/codex-mini-latest", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2025-11-17", "shutdown_date": "2026-02-12", "replacement": "`gpt-5-codex-mini`", "phase": "past", "section": "2025-11-17: `codex-mini-latest` model snapshot", "source": "https://developers.openai.com/api/docs/deprecations#2025-11-17-codex-mini-latest-model-snapshot" } ], "shutdown_date": "2026-02-12", "intro": "codex-mini-latest is a fine-tuned version of o4-mini specifically for use in Codex CLI. For direct use in the API, we recommend starting with gpt-4.1.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "failure", "http_status": 404, "request_note": "GET /v1/models/codex-mini-latest -> 404 (a 404 with our key never means the model does not exist)", "get_model": { "status": 404, "error_type": "invalid_request_error", "error_code": "model_not_found", "error_message": "The model 'codex-mini-latest' does not exist" } }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/codex-mini-latest", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-11-17-codex-mini-latest-model-snapshot", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "computer-use-preview", "record_kind": "model", "canonical_model": "computer-use-preview", "display_name": "computer-use-preview", "description": "Specialized model for computer use tool", "aliases": [], "snapshots": [ "computer-use-preview-2025-03-11" ], "default_snapshot": "computer-use-preview-2025-03-11", "family": "computer-use", "status": [ "DOCUMENTED", "RETIRED", "PREVIEW" ], "flags": [], "release_date": "2025-03-11", "release_date_source": "changelog", "knowledge_cutoff": "2023-10-01", "context_window": 8192, "max_input": null, "max_output": 1024, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": "unknown", "tool_file_search": "unknown", "tool_code_interpreter": "unknown", "tool_image_generation": "unknown", "tool_mcp": "unknown", "tool_computer_use": true, "tool_hosted_shell": "unknown", "tool_apply_patch": "unknown", "tool_skills": "unknown", "tool_tool_search": "unknown", "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [], "features_documented": [ "function_calling" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 3.0, "unit": "1M tokens" }, "Output": { "price": 12.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 3": { "RPM": 3000, "TPM": 20000000, "Batch queue limit": 450000000 }, "Tier 4": { "RPM": 3000, "TPM": 20000000, "Batch queue limit": 450000000 }, "Tier 5": { "RPM": 3000, "TPM": 20000000, "Batch queue limit": 450000000 } } } }, "source": "https://developers.openai.com/api/docs/models/computer-use-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-07-23", "replacement": "`gpt-5.6-terra`", "phase": "past", "section": "2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown" } ], "shutdown_date": "2026-07-23", "intro": "The computer-use-preview model is a specialized model for the computer use tool. It is trained to understand and execute computer tasks. See the [computer use guide](/api/docs/guides/tools-computer-use) for more information. This model is only usable in the [Responses API](/api/docs/api-reference/responses).", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "failure", "http_status": 404, "request_note": "GET /v1/models/computer-use-preview -> 404 (a 404 with our key never means the model does not exist)", "get_model": { "status": 404, "error_type": "invalid_request_error", "error_code": "model_not_found", "error_message": "The model 'computer-use-preview' does not exist" } }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/computer-use-preview", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "computer-use-preview-2025-03-11", "record_kind": "snapshot", "canonical_model": "computer-use-preview", "display_name": "computer-use-preview (snapshot computer-use-preview-2025-03-11)", "description": "Specialized model for computer use tool", "aliases": [], "snapshots": [], "default_snapshot": "computer-use-preview-2025-03-11", "family": "computer-use", "status": [ "DOCUMENTED", "RETIRED", "PREVIEW" ], "flags": [], "release_date": "2025-03-11", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 8192, "max_input": null, "max_output": 1024, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": "unknown", "tool_file_search": "unknown", "tool_code_interpreter": "unknown", "tool_image_generation": "unknown", "tool_mcp": "unknown", "tool_computer_use": true, "tool_hosted_shell": "unknown", "tool_apply_patch": "unknown", "tool_skills": "unknown", "tool_tool_search": "unknown", "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [], "features_documented": [ "function_calling" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 3.0, "unit": "1M tokens" }, "Output": { "price": 12.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 3": { "RPM": 3000, "TPM": 20000000, "Batch queue limit": 450000000 }, "Tier 4": { "RPM": 3000, "TPM": 20000000, "Batch queue limit": 450000000 }, "Tier 5": { "RPM": 3000, "TPM": 20000000, "Batch queue limit": 450000000 } } } }, "source": "https://developers.openai.com/api/docs/models/computer-use-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-07-23", "replacement": "`gpt-5.6-terra`", "phase": "past", "section": "2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown" } ], "shutdown_date": "2026-07-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/computer-use-preview", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "curie", "record_kind": "id_only", "canonical_model": "curie", "display_name": "curie", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "legacy-retired", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`davinci-002`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" }, { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`davinci-002`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "dall-e-2", "record_kind": "id_only", "canonical_model": "dall-e-2", "display_name": "dall-e-2", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "image", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2025-11-14", "shutdown_date": "2026-05-12", "replacement": "`gpt-image-2`, `gpt-image-1`, or `gpt-image-1-mini`", "phase": "past", "section": "2025-11-14: DALL·E model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2025-11-14-dall-e-model-snapshots" } ], "shutdown_date": "2026-05-12", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2025-11-14-dall-e-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "dall-e-3", "record_kind": "model", "canonical_model": "dall-e-3", "display_name": "DALL·E 3", "description": "Deprecated image generation model", "aliases": [], "snapshots": [], "default_snapshot": "dall-e-3", "family": "image", "status": [ "DOCUMENTED", "RETIRED" ], "flags": [], "release_date": "2023-11-06", "release_date_source": "changelog", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text" ], "output": [ "image" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": false, "image_in": false, "image_out": true, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": "unknown", "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": true, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Image generation", "route": "/v1/images/generations" } ], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM" ], "note": null, "tiers": { "Tier free": { "RPM": "1 img/min" }, "Tier 1": { "RPM": "500 img/min" }, "Tier 2": { "RPM": "2500 img/min" }, "Tier 3": { "RPM": "5000 img/min" }, "Tier 4": { "RPM": "7500 img/min" }, "Tier 5": { "RPM": "10000 img/min" } } } }, "source": "https://developers.openai.com/api/docs/models/dall-e-3", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2025-11-14", "shutdown_date": "2026-05-12", "replacement": "`gpt-image-2`, `gpt-image-1`, or `gpt-image-1-mini`", "phase": "past", "section": "2025-11-14: DALL·E model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2025-11-14-dall-e-model-snapshots" } ], "shutdown_date": "2026-05-12", "intro": "DALL·E 3 has been deprecated and removed from the API. We recommend [GPT-Image-2.5 Sunburst](/api/docs/models/gpt-image-2.5-sunburst) for current image generation and editing.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "failure", "http_status": 404, "request_note": "GET /v1/models/dall-e-3 -> 404 (a 404 with our key never means the model does not exist)", "get_model": { "status": 404, "error_type": "invalid_request_error", "error_code": "model_not_found", "error_message": "The model 'dall-e-3' does not exist" } }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/dall-e-3", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-11-14-dall-e-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "davinci", "record_kind": "id_only", "canonical_model": "davinci", "display_name": "davinci", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "legacy-retired", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`davinci-002`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" }, { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`davinci-002`, `gpt-3.5-turbo`, `gpt-4o`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "davinci-002", "record_kind": "model", "canonical_model": "davinci-002", "display_name": "davinci-002", "description": "Replacement for the GPT-3 curie and davinci base models", "aliases": [], "snapshots": [], "default_snapshot": "davinci-002", "family": "base-legacy", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED", "LEGACY" ], "flags": [], "release_date": "2023-08-21", "release_date_source": "GET /v1/models created timestamp (approximation)", "knowledge_cutoff": "2021-09-01", "context_window": null, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": true, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Completions (legacy)", "route": "/v1/completions" } ], "tools": [], "features_documented": [ "fine_tuning" ], "pricing": { "standard": { "input": 2.0, "_unit": "per 1M tokens", "output": 2.0, "fine_tuning_training": 6.0, "fine_tuned_input": 12.0, "fine_tuned_output": 12.0 }, "batch": { "input": 1.0, "_unit": "per 1M tokens", "output": 1.0, "fine_tuning_training": 6.0, "fine_tuned_input": 6.0, "fine_tuned_output": 6.0 }, "model_page:Text tokens": { "Input": { "price": 2.0, "unit": "1M tokens" }, "Output": { "price": 2.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 10000, "Batch queue limit": 100000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 40000, "Batch queue limit": 200000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 80000, "Batch queue limit": 5000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 300000, "Batch queue limit": 30000000 }, "Tier 5": { "RPM": 10000, "RPD": null, "TPM": 1000000, "Batch queue limit": 150000000 } } } }, "source": "https://developers.openai.com/api/docs/models/davinci-002", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1692634301, "openapi_enum": true }, "deprecation": [ { "announced": "2025-09-26", "shutdown_date": "2026-09-28", "replacement": "`gpt-5.6-terra`", "phase": "upcoming", "section": "2025-09-26: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2025-09-26-legacy-gpt-model-snapshots" }, { "announced": "2024-08-29", "shutdown_date": "2024-10-28", "replacement": "`gpt-4o-mini`", "phase": "past", "section": "2024-08-29: Fine-tuning training on babbage-002 and davinci-002 models", "source": "https://developers.openai.com/api/docs/deprecations#2024-08-29-fine-tuning-training-on-babbage-002-and-davinci-002-models" }, { "announced": null, "shutdown_date": "2026-09-28", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-09-28", "intro": "GPT base models can understand and generate natural language or code but are not trained with instruction following. These models are made to be replacements for our original GPT-3 base models and use the legacy Completions API. Most customers should use GPT-3.5 or GPT-4.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/davinci-002", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-09-26-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2024-08-29-fine-tuning-training-on-babbage-002-and-davinci-002-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-3.5-turbo", "record_kind": "model", "canonical_model": "gpt-3.5-turbo", "display_name": "GPT-3.5 Turbo", "description": "Legacy GPT model for cheaper chat and non-chat tasks", "aliases": [ "gpt-3.5-turbo-instruct" ], "snapshots": [ "gpt-3.5-turbo-0125", "gpt-3.5-turbo-1106" ], "default_snapshot": "gpt-3.5-turbo-0125", "family": "gpt-3.5", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED", "LEGACY" ], "flags": [], "release_date": "2023-02-28", "release_date_source": "GET /v1/models created timestamp (approximation)", "knowledge_cutoff": "2021-09-01", "context_window": 16385, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": "unknown", "tool_file_search": "unknown", "tool_code_interpreter": "unknown", "tool_image_generation": "unknown", "tool_mcp": "unknown", "tool_computer_use": "unknown", "tool_hosted_shell": "unknown", "tool_apply_patch": "unknown", "tool_skills": "unknown", "tool_tool_search": "unknown", "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [], "features_documented": [ "fine_tuning" ], "pricing": { "standard": { "input": 0.5, "_unit": "per 1M tokens", "output": 1.5, "fine_tuning_training": 8.0, "fine_tuned_input": 3.0, "fine_tuned_output": 6.0 }, "batch": { "fine_tuning_training": 8.0, "_unit": "per 1M training tokens", "fine_tuned_input": 1.5, "fine_tuned_output": 3.0 }, "model_page:Text tokens": { "Input": { "price": 0.5, "unit": "1M tokens" }, "Output": { "price": 1.5, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 2000000, "Batch queue limit": 5000000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 4000000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 10000, "RPD": null, "TPM": 50000000, "Batch queue limit": 10000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-3.5-turbo", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "openai", "created_ts": 1677610602, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-terra`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" }, { "announced": null, "shutdown_date": "2026-10-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-10-23", "intro": "GPT-3.5 Turbo models can understand and generate natural language or code and have been optimized for chat using the Chat Completions API but work well for non-chat tasks as well. As of July 2024, use gpt-4o-mini in place of GPT-3.5 Turbo, as it is cheaper, more capable, multimodal, and just as fast. GPT-3.5 Turbo is still available for use in the API.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-3.5-turbo", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-3.5-turbo-0125", "record_kind": "snapshot", "canonical_model": "gpt-3.5-turbo", "display_name": "GPT-3.5 Turbo (snapshot gpt-3.5-turbo-0125)", "description": "Legacy GPT model for cheaper chat and non-chat tasks", "aliases": [], "snapshots": [], "default_snapshot": "gpt-3.5-turbo-0125", "family": "gpt-3.5", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED", "LEGACY" ], "flags": [], "release_date": "2024-01-25", "release_date_source": "changelog", "knowledge_cutoff": "2021-09-01", "context_window": 16385, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": "unknown", "tool_file_search": "unknown", "tool_code_interpreter": "unknown", "tool_image_generation": "unknown", "tool_mcp": "unknown", "tool_computer_use": "unknown", "tool_hosted_shell": "unknown", "tool_apply_patch": "unknown", "tool_skills": "unknown", "tool_tool_search": "unknown", "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [], "features_documented": [ "fine_tuning" ], "pricing": { "standard": { "input": 0.5, "_unit": "per 1M tokens", "output": 1.5, "fine_tuning_training": 8.0, "fine_tuned_input": 3.0, "fine_tuned_output": 6.0 }, "batch": { "fine_tuning_training": 8.0, "_unit": "per 1M training tokens", "fine_tuned_input": 1.5, "fine_tuned_output": 3.0 }, "model_page:Text tokens": { "Input": { "price": 0.5, "unit": "1M tokens" }, "Output": { "price": 1.5, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 2000000, "Batch queue limit": 5000000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 4000000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 10000, "RPD": null, "TPM": 50000000, "Batch queue limit": 10000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-3.5-turbo", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1706048358, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-terra`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" }, { "announced": null, "shutdown_date": "2026-10-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-10-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-3.5-turbo", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-3.5-turbo-0301", "record_kind": "id_only", "canonical_model": "gpt-3.5-turbo-0301", "display_name": "gpt-3.5-turbo-0301", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "gpt-3.5", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2023-06-13", "shutdown_date": "2024-09-13", "replacement": "`gpt-3.5-turbo`", "phase": "past", "section": "2023-06-13: Updated chat models", "source": "https://developers.openai.com/api/docs/deprecations#2023-06-13-updated-chat-models" } ], "shutdown_date": "2024-09-13", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-06-13-updated-chat-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-3.5-turbo-0613", "record_kind": "id_only", "canonical_model": "gpt-3.5-turbo-0613", "display_name": "gpt-3.5-turbo-0613", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "gpt-3.5", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2023-11-06", "shutdown_date": "2024-09-13", "replacement": "`gpt-3.5-turbo`", "phase": "past", "section": "2023-11-06: Chat model updates", "source": "https://developers.openai.com/api/docs/deprecations#2023-11-06-chat-model-updates" } ], "shutdown_date": "2024-09-13", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-11-06-chat-model-updates", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-3.5-turbo-1106", "record_kind": "snapshot", "canonical_model": "gpt-3.5-turbo", "display_name": "GPT-3.5 Turbo (snapshot gpt-3.5-turbo-1106)", "description": "Legacy GPT model for cheaper chat and non-chat tasks", "aliases": [], "snapshots": [], "default_snapshot": "gpt-3.5-turbo-0125", "family": "gpt-3.5", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED", "LEGACY" ], "flags": [], "release_date": "2023-11-06", "release_date_source": "changelog", "knowledge_cutoff": "2021-09-01", "context_window": 16385, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": "unknown", "tool_file_search": "unknown", "tool_code_interpreter": "unknown", "tool_image_generation": "unknown", "tool_mcp": "unknown", "tool_computer_use": "unknown", "tool_hosted_shell": "unknown", "tool_apply_patch": "unknown", "tool_skills": "unknown", "tool_tool_search": "unknown", "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [], "features_documented": [ "fine_tuning" ], "pricing": { "standard": { "input": 0.5, "_unit": "per 1M tokens", "output": 1.5, "fine_tuning_training": 8.0, "fine_tuned_input": 3.0, "fine_tuned_output": 6.0 }, "batch": { "fine_tuning_training": 8.0, "_unit": "per 1M training tokens", "fine_tuned_input": 1.5, "fine_tuned_output": 3.0 }, "model_page:Text tokens": { "Input": { "price": 0.5, "unit": "1M tokens" }, "Output": { "price": 1.5, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 2000000, "Batch queue limit": 5000000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 4000000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 10000, "RPD": null, "TPM": 50000000, "Batch queue limit": 10000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-3.5-turbo", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1698959748, "openapi_enum": true }, "deprecation": [ { "announced": "2025-09-26", "shutdown_date": "2026-09-28", "replacement": "`gpt-5.6-terra`", "phase": "upcoming", "section": "2025-09-26: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2025-09-26-legacy-gpt-model-snapshots" }, { "announced": null, "shutdown_date": "2026-09-28", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-09-28", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-3.5-turbo", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-09-26-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-3.5-turbo-16k", "record_kind": "id_only", "canonical_model": "gpt-3.5-turbo-16k", "display_name": "gpt-3.5-turbo-16k", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "gpt-3.5", "status": [ "LIVE_VERIFIED", "LIVE_DISCOVERED", "LEGACY" ], "flags": [ "DOCUMENTATION_INCOMPLETE" ], "release_date": "2023-05-10", "release_date_source": "GET /v1/models created timestamp (approximation)", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "openai-internal", "created_ts": 1683758102, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models/gpt-3.5-turbo-16k -> 200", "get_model": { "status": 200, "id": "gpt-3.5-turbo-16k", "object": "model", "created": 1683758102, "owned_by": "openai-internal", "shutdown_date": null } }, "sources": [ { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-3.5-turbo-16k-0613", "record_kind": "id_only", "canonical_model": "gpt-3.5-turbo-16k-0613", "display_name": "gpt-3.5-turbo-16k-0613", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "gpt-3.5", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2023-11-06", "shutdown_date": "2024-09-13", "replacement": "`gpt-3.5-turbo`", "phase": "past", "section": "2023-11-06: Chat model updates", "source": "https://developers.openai.com/api/docs/deprecations#2023-11-06-chat-model-updates" } ], "shutdown_date": "2024-09-13", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-11-06-chat-model-updates", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-3.5-turbo-completions", "record_kind": "id_only", "canonical_model": "gpt-3.5-turbo-completions", "display_name": "gpt-3.5-turbo-completions", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "gpt-3.5", "status": [ "DEPRECATED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-terra`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" } ], "shutdown_date": "2026-10-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-3.5-turbo-instruct", "record_kind": "alias", "canonical_model": "gpt-3.5-turbo", "display_name": "GPT-3.5 Turbo (alias gpt-3.5-turbo-instruct)", "description": "Legacy GPT model for cheaper chat and non-chat tasks", "aliases": [], "snapshots": [], "default_snapshot": "gpt-3.5-turbo-0125", "family": "gpt-3.5", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED", "LEGACY" ], "flags": [], "release_date": "2023-08-24", "release_date_source": "GET /v1/models created timestamp (approximation)", "knowledge_cutoff": "2021-09-01", "context_window": 16385, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": "unknown", "tool_file_search": "unknown", "tool_code_interpreter": "unknown", "tool_image_generation": "unknown", "tool_mcp": "unknown", "tool_computer_use": "unknown", "tool_hosted_shell": "unknown", "tool_apply_patch": "unknown", "tool_skills": "unknown", "tool_tool_search": "unknown", "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [], "features_documented": [ "fine_tuning" ], "pricing": { "standard": { "input": 0.5, "_unit": "per 1M tokens", "output": 1.5, "fine_tuning_training": 8.0, "fine_tuned_input": 3.0, "fine_tuned_output": 6.0 }, "batch": { "fine_tuning_training": 8.0, "_unit": "per 1M training tokens", "fine_tuned_input": 1.5, "fine_tuned_output": 3.0 }, "model_page:Text tokens": { "Input": { "price": 0.5, "unit": "1M tokens" }, "Output": { "price": 1.5, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 2000000, "Batch queue limit": 5000000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 4000000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 10000, "RPD": null, "TPM": 50000000, "Batch queue limit": 10000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-3.5-turbo", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1692901427, "openapi_enum": true }, "deprecation": [ { "announced": "2025-09-26", "shutdown_date": "2026-09-28", "replacement": "`gpt-5.6-terra`", "phase": "upcoming", "section": "2025-09-26: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2025-09-26-legacy-gpt-model-snapshots" }, { "announced": null, "shutdown_date": "2026-09-28", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-09-28", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-3.5-turbo", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-09-26-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-3.5-turbo-instruct-0914", "record_kind": "id_only", "canonical_model": "gpt-3.5-turbo-instruct-0914", "display_name": "gpt-3.5-turbo-instruct-0914", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "gpt-3.5", "status": [ "LIVE_VERIFIED", "LIVE_DISCOVERED", "LEGACY" ], "flags": [ "DOCUMENTATION_INCOMPLETE" ], "release_date": "2023-09-07", "release_date_source": "GET /v1/models created timestamp (approximation)", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1694122472, "openapi_enum": false }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4", "record_kind": "model", "canonical_model": "gpt-4", "display_name": "GPT-4", "description": "An older high-intelligence GPT model", "aliases": [], "snapshots": [ "gpt-4-0613", "gpt-4-0314" ], "default_snapshot": "gpt-4-0613", "family": "gpt-4", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED", "LEGACY" ], "flags": [], "release_date": "2023-06-27", "release_date_source": "GET /v1/models created timestamp (approximation)", "knowledge_cutoff": "2023-12-01", "context_window": 8192, "max_input": null, "max_output": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": "unknown", "tool_file_search": "unknown", "tool_code_interpreter": "unknown", "tool_image_generation": "unknown", "tool_mcp": "unknown", "tool_computer_use": "unknown", "tool_hosted_shell": "unknown", "tool_apply_patch": "unknown", "tool_skills": "unknown", "tool_tool_search": "unknown", "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [], "features_documented": [ "fine_tuning", "streaming" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 30.0, "unit": "1M tokens" }, "Output": { "price": 60.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 10000, "Batch queue limit": 100000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 40000, "Batch queue limit": 200000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 80000, "Batch queue limit": 5000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 300000, "Batch queue limit": 30000000 }, "Tier 5": { "RPM": 10000, "RPD": null, "TPM": 1000000, "Batch queue limit": 150000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "openai", "created_ts": 1687882411, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-sol`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" }, { "announced": null, "shutdown_date": "2026-10-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-10-23", "intro": "GPT-4 is an older version of a high-intelligence GPT model, usable in Chat Completions.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4-0125-preview", "record_kind": "alias", "canonical_model": "gpt-4-turbo-preview", "display_name": "GPT-4 Turbo Preview (alias gpt-4-0125-preview)", "description": "An older fast GPT model", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4-0125-preview", "family": "gpt-4", "status": [ "DOCUMENTED", "RETIRED", "PREVIEW" ], "flags": [], "release_date": "2023-11-06", "release_date_source": "changelog (parent model)", "knowledge_cutoff": "2023-12-01", "context_window": 128000, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": "unknown", "tool_file_search": "unknown", "tool_code_interpreter": "unknown", "tool_image_generation": "unknown", "tool_mcp": "unknown", "tool_computer_use": "unknown", "tool_hosted_shell": "unknown", "tool_apply_patch": "unknown", "tool_skills": "unknown", "tool_tool_search": "unknown", "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" } ], "tools": [], "features_documented": [ "fine_tuning" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 10.0, "unit": "1M tokens" }, "Output": { "price": 30.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 600000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 800000, "Batch queue limit": 80000000 }, "Tier 5": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 300000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4-turbo-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2025-09-26", "shutdown_date": "2026-03-26", "replacement": "`gpt-5` or `gpt-4.1*`", "phase": "past", "section": "2025-09-26: Legacy GPT model snapshots (March 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2025-09-26-legacy-gpt-model-snapshots-march-2026-shutdown" } ], "shutdown_date": "2026-03-26", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4-turbo-preview", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-09-26-legacy-gpt-model-snapshots-march-2026-shutdown", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4-0314", "record_kind": "snapshot", "canonical_model": "gpt-4", "display_name": "GPT-4 (snapshot gpt-4-0314)", "description": "An older high-intelligence GPT model", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4-0613", "family": "gpt-4", "status": [ "DOCUMENTED", "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": "2023-12-01", "context_window": 8192, "max_input": null, "max_output": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": "unknown", "tool_file_search": "unknown", "tool_code_interpreter": "unknown", "tool_image_generation": "unknown", "tool_mcp": "unknown", "tool_computer_use": "unknown", "tool_hosted_shell": "unknown", "tool_apply_patch": "unknown", "tool_skills": "unknown", "tool_tool_search": "unknown", "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [], "features_documented": [ "fine_tuning", "streaming" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 30.0, "unit": "1M tokens" }, "Output": { "price": 60.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 10000, "Batch queue limit": 100000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 40000, "Batch queue limit": 200000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 80000, "Batch queue limit": 5000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 300000, "Batch queue limit": 30000000 }, "Tier 5": { "RPM": 10000, "RPD": null, "TPM": 1000000, "Batch queue limit": 150000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2025-09-26", "shutdown_date": "2026-03-26", "replacement": "`gpt-5` or `gpt-4.1*`", "phase": "past", "section": "2025-09-26: Legacy GPT model snapshots (March 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2025-09-26-legacy-gpt-model-snapshots-march-2026-shutdown" }, { "announced": "2023-06-13", "shutdown_date": "2024-06-13", "replacement": "`gpt-4o`", "phase": "past", "section": "2023-06-13: Updated chat models", "source": "https://developers.openai.com/api/docs/deprecations#2023-06-13-updated-chat-models" } ], "shutdown_date": "2026-03-26", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-09-26-legacy-gpt-model-snapshots-march-2026-shutdown", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2023-06-13-updated-chat-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4-0613", "record_kind": "snapshot", "canonical_model": "gpt-4", "display_name": "GPT-4 (snapshot gpt-4-0613)", "description": "An older high-intelligence GPT model", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4-0613", "family": "gpt-4", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED", "LEGACY" ], "flags": [], "release_date": "2023-06-12", "release_date_source": "GET /v1/models created timestamp (approximation)", "knowledge_cutoff": "2023-12-01", "context_window": 8192, "max_input": null, "max_output": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": "unknown", "tool_file_search": "unknown", "tool_code_interpreter": "unknown", "tool_image_generation": "unknown", "tool_mcp": "unknown", "tool_computer_use": "unknown", "tool_hosted_shell": "unknown", "tool_apply_patch": "unknown", "tool_skills": "unknown", "tool_tool_search": "unknown", "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [], "features_documented": [ "fine_tuning", "streaming" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 30.0, "unit": "1M tokens" }, "Output": { "price": 60.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 10000, "Batch queue limit": 100000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 40000, "Batch queue limit": 200000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 80000, "Batch queue limit": 5000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 300000, "Batch queue limit": 30000000 }, "Tier 5": { "RPM": 10000, "RPD": null, "TPM": 1000000, "Batch queue limit": 150000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "openai", "created_ts": 1686588896, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-sol`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" }, { "announced": null, "shutdown_date": "2026-10-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-10-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4-0613-completions", "record_kind": "id_only", "canonical_model": "gpt-4-0613-completions", "display_name": "gpt-4-0613-completions", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "gpt-4", "status": [ "DEPRECATED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-sol`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" } ], "shutdown_date": "2026-10-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4-1106-preview", "record_kind": "id_only", "canonical_model": "gpt-4-1106-preview", "display_name": "gpt-4-1106-preview", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "gpt-4", "status": [ "DEPRECATED", "PREVIEW" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-sol`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" }, { "announced": "2025-09-26", "shutdown_date": "2026-03-26", "replacement": "`gpt-5` or `gpt-4.1*`", "phase": "past", "section": "2025-09-26: Legacy GPT model snapshots (March 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2025-09-26-legacy-gpt-model-snapshots-march-2026-shutdown" } ], "shutdown_date": "2026-10-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-09-26-legacy-gpt-model-snapshots-march-2026-shutdown", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4-1106-vision-preview", "record_kind": "alias", "canonical_model": "gpt-4-turbo-preview", "display_name": "GPT-4 Turbo Preview (alias gpt-4-1106-vision-preview)", "description": "An older fast GPT model", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4-0125-preview", "family": "gpt-4", "status": [ "DOCUMENTED", "RETIRED", "PREVIEW" ], "flags": [], "release_date": "2023-11-06", "release_date_source": "changelog (parent model)", "knowledge_cutoff": "2023-12-01", "context_window": 128000, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": "unknown", "tool_file_search": "unknown", "tool_code_interpreter": "unknown", "tool_image_generation": "unknown", "tool_mcp": "unknown", "tool_computer_use": "unknown", "tool_hosted_shell": "unknown", "tool_apply_patch": "unknown", "tool_skills": "unknown", "tool_tool_search": "unknown", "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" } ], "tools": [], "features_documented": [ "fine_tuning" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 10.0, "unit": "1M tokens" }, "Output": { "price": 30.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 600000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 800000, "Batch queue limit": 80000000 }, "Tier 5": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 300000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4-turbo-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2024-06-06", "shutdown_date": "2024-12-06", "replacement": "`gpt-4o`", "phase": "past", "section": "2024-06-06: GPT-4-32K and Vision Preview models", "source": "https://developers.openai.com/api/docs/deprecations#2024-06-06-gpt-4-32k-and-vision-preview-models" } ], "shutdown_date": "2024-12-06", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4-turbo-preview", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2024-06-06-gpt-4-32k-and-vision-preview-models", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4-32k", "record_kind": "id_only", "canonical_model": "gpt-4-32k", "display_name": "gpt-4-32k", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "gpt-4", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2024-06-06", "shutdown_date": "2025-06-06", "replacement": "`gpt-4o`", "phase": "past", "section": "2024-06-06: GPT-4-32K and Vision Preview models", "source": "https://developers.openai.com/api/docs/deprecations#2024-06-06-gpt-4-32k-and-vision-preview-models" } ], "shutdown_date": "2025-06-06", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2024-06-06-gpt-4-32k-and-vision-preview-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4-32k-0314", "record_kind": "id_only", "canonical_model": "gpt-4-32k-0314", "display_name": "gpt-4-32k-0314", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "gpt-4", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2024-06-06", "shutdown_date": "2025-06-06", "replacement": "`gpt-4o`", "phase": "past", "section": "2024-06-06: GPT-4-32K and Vision Preview models", "source": "https://developers.openai.com/api/docs/deprecations#2024-06-06-gpt-4-32k-and-vision-preview-models" }, { "announced": "2023-06-13", "shutdown_date": "2025-06-06", "replacement": "`gpt-4o`", "phase": "past", "section": "2023-06-13: Updated chat models", "source": "https://developers.openai.com/api/docs/deprecations#2023-06-13-updated-chat-models" } ], "shutdown_date": "2025-06-06", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2024-06-06-gpt-4-32k-and-vision-preview-models", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2023-06-13-updated-chat-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4-32k-0613", "record_kind": "id_only", "canonical_model": "gpt-4-32k-0613", "display_name": "gpt-4-32k-0613", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "gpt-4", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2024-06-06", "shutdown_date": "2025-06-06", "replacement": "`gpt-4o`", "phase": "past", "section": "2024-06-06: GPT-4-32K and Vision Preview models", "source": "https://developers.openai.com/api/docs/deprecations#2024-06-06-gpt-4-32k-and-vision-preview-models" } ], "shutdown_date": "2025-06-06", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2024-06-06-gpt-4-32k-and-vision-preview-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4-completions", "record_kind": "id_only", "canonical_model": "gpt-4-completions", "display_name": "gpt-4-completions", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "gpt-4", "status": [ "DEPRECATED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-sol`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" } ], "shutdown_date": "2026-10-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4-turbo", "record_kind": "model", "canonical_model": "gpt-4-turbo", "display_name": "GPT-4 Turbo", "description": "An older high-intelligence GPT model", "aliases": [], "snapshots": [ "gpt-4-turbo-2024-04-09" ], "default_snapshot": "gpt-4-turbo-2024-04-09", "family": "gpt-4", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED", "LEGACY" ], "flags": [], "release_date": "2024-04-09", "release_date_source": "changelog", "knowledge_cutoff": "2023-12-01", "context_window": 128000, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": "unknown", "tool_file_search": "unknown", "tool_code_interpreter": "unknown", "tool_image_generation": "unknown", "tool_mcp": "unknown", "tool_computer_use": "unknown", "tool_hosted_shell": "unknown", "tool_apply_patch": "unknown", "tool_skills": "unknown", "tool_tool_search": "unknown", "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [], "features_documented": [ "function_calling", "image_input", "streaming" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 10.0, "unit": "1M tokens" }, "Output": { "price": 30.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 600000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 800000, "Batch queue limit": 80000000 }, "Tier 5": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 300000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4-turbo", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1712361441, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-sol`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" }, { "announced": null, "shutdown_date": "2026-10-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-10-23", "intro": "GPT-4 Turbo is the next generation of GPT-4, an older high-intelligence GPT model. It was designed to be a cheaper, better version of GPT-4. Today, we recommend using a newer model like GPT-4o.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4-turbo", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4-turbo-2024-04-09", "record_kind": "snapshot", "canonical_model": "gpt-4-turbo", "display_name": "GPT-4 Turbo (snapshot gpt-4-turbo-2024-04-09)", "description": "An older high-intelligence GPT model", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4-turbo-2024-04-09", "family": "gpt-4", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED", "LEGACY" ], "flags": [], "release_date": "2024-04-09", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-12-01", "context_window": 128000, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": "unknown", "tool_file_search": "unknown", "tool_code_interpreter": "unknown", "tool_image_generation": "unknown", "tool_mcp": "unknown", "tool_computer_use": "unknown", "tool_hosted_shell": "unknown", "tool_apply_patch": "unknown", "tool_skills": "unknown", "tool_tool_search": "unknown", "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [], "features_documented": [ "function_calling", "image_input", "streaming" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 10.0, "unit": "1M tokens" }, "Output": { "price": 30.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 600000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 800000, "Batch queue limit": 80000000 }, "Tier 5": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 300000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4-turbo", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1712601677, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-sol`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" }, { "announced": null, "shutdown_date": "2026-10-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-10-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4-turbo", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4-turbo-completions", "record_kind": "id_only", "canonical_model": "gpt-4-turbo-completions", "display_name": "gpt-4-turbo-completions", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "gpt-4", "status": [ "DEPRECATED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-sol`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" } ], "shutdown_date": "2026-10-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4-turbo-preview", "record_kind": "model", "canonical_model": "gpt-4-turbo-preview", "display_name": "GPT-4 Turbo Preview", "description": "An older fast GPT model", "aliases": [ "gpt-4-0125-preview", "gpt-4-1106-vision-preview" ], "snapshots": [], "default_snapshot": "gpt-4-0125-preview", "family": "gpt-4", "status": [ "DOCUMENTED", "RETIRED", "PREVIEW", "LEGACY" ], "flags": [], "release_date": "2023-11-06", "release_date_source": "changelog", "knowledge_cutoff": "2023-12-01", "context_window": 128000, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": "unknown", "tool_file_search": "unknown", "tool_code_interpreter": "unknown", "tool_image_generation": "unknown", "tool_mcp": "unknown", "tool_computer_use": "unknown", "tool_hosted_shell": "unknown", "tool_apply_patch": "unknown", "tool_skills": "unknown", "tool_tool_search": "unknown", "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" } ], "tools": [], "features_documented": [ "fine_tuning" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 10.0, "unit": "1M tokens" }, "Output": { "price": 30.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 600000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 800000, "Batch queue limit": 80000000 }, "Tier 5": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 300000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4-turbo-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2025-09-26", "shutdown_date": "2026-03-26", "replacement": "`gpt-5` or `gpt-4.1*`", "phase": "past", "section": "2025-09-26: Legacy GPT model snapshots (March 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2025-09-26-legacy-gpt-model-snapshots-march-2026-shutdown" } ], "shutdown_date": "2026-03-26", "intro": "This is a research preview of the GPT-4 Turbo model, an older high-intelligence GPT model.", "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4-turbo-preview", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-09-26-legacy-gpt-model-snapshots-march-2026-shutdown", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4-turbo-preview-completions", "record_kind": "id_only", "canonical_model": "gpt-4-turbo-preview-completions", "display_name": "gpt-4-turbo-preview-completions", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "gpt-4", "status": [ "RETIRED", "PREVIEW" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2025-09-26", "shutdown_date": "2026-03-26", "replacement": "`gpt-5` or `gpt-4.1*`", "phase": "past", "section": "2025-09-26: Legacy GPT model snapshots (March 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2025-09-26-legacy-gpt-model-snapshots-march-2026-shutdown" } ], "shutdown_date": "2026-03-26", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2025-09-26-legacy-gpt-model-snapshots-march-2026-shutdown", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4-vision-preview", "record_kind": "id_only", "canonical_model": "gpt-4-vision-preview", "display_name": "gpt-4-vision-preview", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "gpt-4", "status": [ "RETIRED", "PREVIEW" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2024-06-06", "shutdown_date": "2024-12-06", "replacement": "`gpt-4o`", "phase": "past", "section": "2024-06-06: GPT-4-32K and Vision Preview models", "source": "https://developers.openai.com/api/docs/deprecations#2024-06-06-gpt-4-32k-and-vision-preview-models" } ], "shutdown_date": "2024-12-06", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2024-06-06-gpt-4-32k-and-vision-preview-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4.1", "record_kind": "model", "canonical_model": "gpt-4.1", "display_name": "GPT-4.1", "description": "Smartest non-reasoning model", "aliases": [], "snapshots": [ "gpt-4.1-2025-04-14" ], "default_snapshot": "gpt-4.1-2025-04-14", "family": "gpt-4.1", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-04-14", "release_date_source": "changelog", "knowledge_cutoff": "2024-06-01", "context_window": 1047576, "max_input": null, "max_output": 32768, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": false, "predicted_outputs": true, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": true, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "file_search", "file_uploads", "fine_tuning", "function_calling", "image_input", "predicted_outputs", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 2.0, "_unit": "per 1M tokens", "cached_input": 0.5, "output": 8.0 }, "batch": { "input": 1.0, "_unit": "per 1M tokens", "output": 4.0 }, "fast": { "input": 3.5, "_unit": "per 1M tokens", "cached_input": 0.875, "output": 14.0 }, "model_page:Text tokens": { "Input": { "price": 2.0, "unit": "1M tokens" }, "Cached input": { "price": 0.5, "unit": "1M tokens" }, "Output": { "price": 8.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } }, "Long Context": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": "128k input tokens", "tiers": { "Tier 1": { "RPM": 100, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 250, "TPM": 500000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 500, "TPM": 1000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 1000, "TPM": 5000000, "Batch queue limit": 100000000 }, "Tier 5": { "RPM": 4000, "TPM": 10000000, "Batch queue limit": 1000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4.1", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1744316542, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-4.1 excels at instruction following and tool calling, with broad knowledge across domains. It features a 1M token context window, and low latency without a reasoning step. Note that we recommend starting with [GPT-5](/api/docs/models/gpt-5) for complex tasks.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4.1", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4.1-2025-04-14", "record_kind": "snapshot", "canonical_model": "gpt-4.1", "display_name": "GPT-4.1 (snapshot gpt-4.1-2025-04-14)", "description": "Smartest non-reasoning model", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4.1-2025-04-14", "family": "gpt-4.1", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-04-14", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2024-06-01", "context_window": 1047576, "max_input": null, "max_output": 32768, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": false, "predicted_outputs": true, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": true, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "file_search", "file_uploads", "fine_tuning", "function_calling", "image_input", "predicted_outputs", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 2.0, "_unit": "per 1M tokens", "cached_input": 0.5, "output": 8.0 }, "batch": { "input": 1.0, "_unit": "per 1M tokens", "output": 4.0 }, "fast": { "input": 3.5, "_unit": "per 1M tokens", "cached_input": 0.875, "output": 14.0 }, "model_page:Text tokens": { "Input": { "price": 2.0, "unit": "1M tokens" }, "Cached input": { "price": 0.5, "unit": "1M tokens" }, "Output": { "price": 8.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } }, "Long Context": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": "128k input tokens", "tiers": { "Tier 1": { "RPM": 100, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 250, "TPM": 500000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 500, "TPM": 1000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 1000, "TPM": 5000000, "Batch queue limit": 100000000 }, "Tier 5": { "RPM": 4000, "TPM": 10000000, "Batch queue limit": 1000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4.1", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1744315746, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4.1", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4.1-mini", "record_kind": "model", "canonical_model": "gpt-4.1-mini", "display_name": "GPT-4.1 Mini", "description": "Smaller, faster version of GPT-4.1", "aliases": [], "snapshots": [ "gpt-4.1-mini-2025-04-14" ], "default_snapshot": "gpt-4.1-mini-2025-04-14", "family": "gpt-4.1", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-04-14", "release_date_source": "changelog", "knowledge_cutoff": "2024-06-01", "context_window": 1047576, "max_input": null, "max_output": 32768, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": true, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": true, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": false, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "mcp", "web_search" ], "features_documented": [ "file_search", "file_uploads", "fine_tuning", "function_calling", "image_input", "predicted_outputs", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 0.4, "_unit": "per 1M tokens", "cached_input": 0.1, "output": 1.6 }, "batch": { "input": 0.2, "_unit": "per 1M tokens", "output": 0.8 }, "fast": { "input": 0.7, "_unit": "per 1M tokens", "cached_input": 0.175, "output": 2.8 }, "model_page:Text tokens": { "Input": { "price": 0.4, "unit": "1M tokens" }, "Cached input": { "price": 0.1, "unit": "1M tokens" }, "Output": { "price": 1.6, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "Standard": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 2000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "RPD": null, "TPM": 150000000, "Batch queue limit": 15000000000 } } }, "Long Context": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": "128k input tokens", "tiers": { "Tier 1": { "RPM": 200, "TPM": 400000, "Batch queue limit": 5000000 }, "Tier 2": { "RPM": 500, "TPM": 1000000, "Batch queue limit": 40000000 }, "Tier 3": { "RPM": 1000, "TPM": 2000000, "Batch queue limit": 80000000 }, "Tier 4": { "RPM": 2000, "TPM": 10000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 8000, "TPM": 20000000, "Batch queue limit": 2000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4.1-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1744318173, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-4.1 Mini excels at instruction following and tool calling. It features a 1M token context window, and low latency without a reasoning step. Note that we recommend starting with [GPT-5 Mini](/api/docs/models/gpt-5-mini) for more complex tasks.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4.1-mini", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4.1-mini-2025-04-14", "record_kind": "snapshot", "canonical_model": "gpt-4.1-mini", "display_name": "GPT-4.1 Mini (snapshot gpt-4.1-mini-2025-04-14)", "description": "Smaller, faster version of GPT-4.1", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4.1-mini-2025-04-14", "family": "gpt-4.1", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-04-14", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2024-06-01", "context_window": 1047576, "max_input": null, "max_output": 32768, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": true, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": true, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": false, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "mcp", "web_search" ], "features_documented": [ "file_search", "file_uploads", "fine_tuning", "function_calling", "image_input", "predicted_outputs", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 0.4, "_unit": "per 1M tokens", "cached_input": 0.1, "output": 1.6 }, "batch": { "input": 0.2, "_unit": "per 1M tokens", "output": 0.8 }, "fast": { "input": 0.7, "_unit": "per 1M tokens", "cached_input": 0.175, "output": 2.8 }, "model_page:Text tokens": { "Input": { "price": 0.4, "unit": "1M tokens" }, "Cached input": { "price": 0.1, "unit": "1M tokens" }, "Output": { "price": 1.6, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "Standard": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 2000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "RPD": null, "TPM": 150000000, "Batch queue limit": 15000000000 } } }, "Long Context": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": "128k input tokens", "tiers": { "Tier 1": { "RPM": 200, "TPM": 400000, "Batch queue limit": 5000000 }, "Tier 2": { "RPM": 500, "TPM": 1000000, "Batch queue limit": 40000000 }, "Tier 3": { "RPM": 1000, "TPM": 2000000, "Batch queue limit": 80000000 }, "Tier 4": { "RPM": 2000, "TPM": 10000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 8000, "TPM": 20000000, "Batch queue limit": 2000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4.1-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1744317547, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4.1-mini", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4.1-nano", "record_kind": "model", "canonical_model": "gpt-4.1-nano", "display_name": "GPT-4.1 nano", "description": "Fastest, most cost-efficient version of GPT-4.1", "aliases": [], "snapshots": [ "gpt-4.1-nano-2025-04-14" ], "default_snapshot": "gpt-4.1-nano-2025-04-14", "family": "gpt-4.1", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-04-14", "release_date_source": "changelog", "knowledge_cutoff": "2024-06-01", "context_window": 1047576, "max_input": null, "max_output": 32768, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": true, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": true, "tool_web_search": false, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp" ], "features_documented": [ "file_search", "file_uploads", "fine_tuning", "function_calling", "image_input", "predicted_outputs", "prompt_caching", "streaming", "structured_outputs" ], "pricing": { "standard": { "input": 0.1, "_unit": "per 1M tokens", "cached_input": 0.025, "output": 0.4 }, "batch": { "input": 0.05, "_unit": "per 1M tokens", "output": 0.2 }, "fast": { "input": 0.2, "_unit": "per 1M tokens", "cached_input": 0.05, "output": 0.8 }, "model_page:Text tokens": { "Input": { "price": 0.1, "unit": "1M tokens" }, "Cached input": { "price": 0.025, "unit": "1M tokens" }, "Output": { "price": 0.4, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "Standard": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 2000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "RPD": null, "TPM": 150000000, "Batch queue limit": 15000000000 } } }, "Long Context": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": "128k input tokens", "tiers": { "Tier 1": { "RPM": 200, "TPM": 400000, "Batch queue limit": 5000000 }, "Tier 2": { "RPM": 500, "TPM": 1000000, "Batch queue limit": 40000000 }, "Tier 3": { "RPM": 1000, "TPM": 2000000, "Batch queue limit": 80000000 }, "Tier 4": { "RPM": 2000, "TPM": 10000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 8000, "TPM": 20000000, "Batch queue limit": 2000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4.1-nano", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1744321707, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-luna`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" }, { "announced": null, "shutdown_date": "2026-10-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-10-23", "intro": "GPT-4.1 nano excels at instruction following and tool calling. It features a 1M token context window, and low latency without a reasoning step. Note that we recommend starting with [GPT-5 nano](/api/docs/models/gpt-5-nano) for more complex tasks.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4.1-nano", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4.1-nano-2025-04-14", "record_kind": "snapshot", "canonical_model": "gpt-4.1-nano", "display_name": "GPT-4.1 nano (snapshot gpt-4.1-nano-2025-04-14)", "description": "Fastest, most cost-efficient version of GPT-4.1", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4.1-nano-2025-04-14", "family": "gpt-4.1", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-04-14", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2024-06-01", "context_window": 1047576, "max_input": null, "max_output": 32768, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": true, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": true, "tool_web_search": false, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp" ], "features_documented": [ "file_search", "file_uploads", "fine_tuning", "function_calling", "image_input", "predicted_outputs", "prompt_caching", "streaming", "structured_outputs" ], "pricing": { "standard": { "input": 0.1, "_unit": "per 1M tokens", "cached_input": 0.025, "output": 0.4 }, "batch": { "input": 0.05, "_unit": "per 1M tokens", "output": 0.2 }, "fast": { "input": 0.2, "_unit": "per 1M tokens", "cached_input": 0.05, "output": 0.8 }, "model_page:Text tokens": { "Input": { "price": 0.1, "unit": "1M tokens" }, "Cached input": { "price": 0.025, "unit": "1M tokens" }, "Output": { "price": 0.4, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "Standard": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 2000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "RPD": null, "TPM": 150000000, "Batch queue limit": 15000000000 } } }, "Long Context": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": "128k input tokens", "tiers": { "Tier 1": { "RPM": 200, "TPM": 400000, "Batch queue limit": 5000000 }, "Tier 2": { "RPM": 500, "TPM": 1000000, "Batch queue limit": 40000000 }, "Tier 3": { "RPM": 1000, "TPM": 2000000, "Batch queue limit": 80000000 }, "Tier 4": { "RPM": 2000, "TPM": 10000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 8000, "TPM": 20000000, "Batch queue limit": 2000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4.1-nano", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1744321025, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-luna`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" }, { "announced": null, "shutdown_date": "2026-10-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-10-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4.1-nano", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4.5-preview", "record_kind": "model", "canonical_model": "gpt-4.5-preview", "display_name": "GPT-4.5 Preview", "description": "Deprecated large model.", "aliases": [], "snapshots": [ "gpt-4.5-preview-2025-02-27" ], "default_snapshot": "gpt-4.5-preview-2025-02-27", "family": "gpt-4.5", "status": [ "DOCUMENTED", "RETIRED", "PREVIEW" ], "flags": [], "release_date": "2025-02-27", "release_date_source": "changelog", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": true, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": "unknown", "tool_file_search": "unknown", "tool_code_interpreter": "unknown", "tool_image_generation": "unknown", "tool_mcp": "unknown", "tool_computer_use": "unknown", "tool_hosted_shell": "unknown", "tool_apply_patch": "unknown", "tool_skills": "unknown", "tool_tool_search": "unknown", "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [], "features_documented": [ "evals", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "system_messages" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 75.0, "unit": "1M tokens" }, "Cached input": { "price": 37.5, "unit": "1M tokens" }, "Output": { "price": 150.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 1000, "TPM": 125000, "Batch queue limit": 50000 }, "Tier 2": { "RPM": 5000, "TPM": 250000, "Batch queue limit": 500000 }, "Tier 3": { "RPM": 5000, "TPM": 500000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 1000000, "Batch queue limit": 100000000 }, "Tier 5": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4.5-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2025-04-14", "shutdown_date": "2025-07-14", "replacement": "`gpt-4.1`", "phase": "past", "section": "2025-04-14: GPT-4.5-preview", "source": "https://developers.openai.com/api/docs/deprecations#2025-04-14-gpt-4-5-preview" } ], "shutdown_date": "2025-07-14", "intro": "Deprecated - a research preview of GPT-4.5. We recommend using gpt-4.1 or o3 models instead for most use cases", "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4.5-preview", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-04-14-gpt-4-5-preview", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4.5-preview-2025-02-27", "record_kind": "snapshot", "canonical_model": "gpt-4.5-preview", "display_name": "GPT-4.5 Preview (snapshot gpt-4.5-preview-2025-02-27)", "description": "Deprecated large model.", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4.5-preview-2025-02-27", "family": "gpt-4.5", "status": [ "DOCUMENTED", "PREVIEW" ], "flags": [], "release_date": "2025-02-27", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": true, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": "unknown", "tool_file_search": "unknown", "tool_code_interpreter": "unknown", "tool_image_generation": "unknown", "tool_mcp": "unknown", "tool_computer_use": "unknown", "tool_hosted_shell": "unknown", "tool_apply_patch": "unknown", "tool_skills": "unknown", "tool_tool_search": "unknown", "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [], "features_documented": [ "evals", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "system_messages" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 75.0, "unit": "1M tokens" }, "Cached input": { "price": 37.5, "unit": "1M tokens" }, "Output": { "price": 150.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 1000, "TPM": 125000, "Batch queue limit": 50000 }, "Tier 2": { "RPM": 5000, "TPM": 250000, "Batch queue limit": 500000 }, "Tier 3": { "RPM": 5000, "TPM": 500000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 1000000, "Batch queue limit": 100000000 }, "Tier 5": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4.5-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4.5-preview", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o", "record_kind": "model", "canonical_model": "gpt-4o", "display_name": "GPT-4o", "description": "Fast, intelligent, flexible GPT model", "aliases": [], "snapshots": [ "gpt-4o-2024-11-20", "gpt-4o-2024-08-06", "gpt-4o-2024-05-13" ], "default_snapshot": "gpt-4o-2024-08-06", "family": "gpt-4o", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2024-05-13", "release_date_source": "changelog", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": true, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "file_search", "file_uploads", "fine_tuning", "function_calling", "image_input", "predicted_outputs", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 2.5, "_unit": "per 1M tokens", "cached_input": 1.25, "output": 10.0 }, "batch": { "input": 1.25, "_unit": "per 1M tokens", "output": 5.0 }, "fast": { "input": 4.25, "_unit": "per 1M tokens", "cached_input": 2.125, "output": 17.0 }, "model_page:Text tokens": { "Input": { "price": 2.5, "unit": "1M tokens" }, "Cached input": { "price": 1.25, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1715367049, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-4o (“o” for “omni”) is our versatile, high-intelligence flagship model. It accepts both text and image inputs, and produces text outputs (including Structured Outputs). It is the best model for most tasks, and is our most capable model outside of our o-series models.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-2024-05-13", "record_kind": "snapshot", "canonical_model": "gpt-4o", "display_name": "GPT-4o (snapshot gpt-4o-2024-05-13)", "description": "Fast, intelligent, flexible GPT model", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4o-2024-08-06", "family": "gpt-4o", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED", "LEGACY" ], "flags": [], "release_date": "2024-05-13", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": true, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "file_search", "file_uploads", "fine_tuning", "function_calling", "image_input", "predicted_outputs", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 2.5, "_unit": "per 1M tokens", "cached_input": 1.25, "output": 10.0 }, "batch": { "input": 1.25, "_unit": "per 1M tokens", "output": 5.0 }, "fast": { "input": 4.25, "_unit": "per 1M tokens", "cached_input": 2.125, "output": 17.0 }, "model_page:Text tokens": { "Input": { "price": 2.5, "unit": "1M tokens" }, "Cached input": { "price": 1.25, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1715368132, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-sol`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" }, { "announced": null, "shutdown_date": "2026-10-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-10-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-2024-08-06", "record_kind": "snapshot", "canonical_model": "gpt-4o", "display_name": "GPT-4o (snapshot gpt-4o-2024-08-06)", "description": "Fast, intelligent, flexible GPT model", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4o-2024-08-06", "family": "gpt-4o", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2024-08-06", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": true, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "file_search", "file_uploads", "fine_tuning", "function_calling", "image_input", "predicted_outputs", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 2.5, "_unit": "per 1M tokens", "cached_input": 1.25, "output": 10.0 }, "batch": { "input": 1.25, "_unit": "per 1M tokens", "output": 5.0 }, "fast": { "input": 4.25, "_unit": "per 1M tokens", "cached_input": 2.125, "output": 17.0 }, "model_page:Text tokens": { "Input": { "price": 2.5, "unit": "1M tokens" }, "Cached input": { "price": 1.25, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1722814719, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-2024-11-20", "record_kind": "snapshot", "canonical_model": "gpt-4o", "display_name": "GPT-4o (snapshot gpt-4o-2024-11-20)", "description": "Fast, intelligent, flexible GPT model", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4o-2024-08-06", "family": "gpt-4o", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2024-11-20", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": true, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "file_search", "file_uploads", "fine_tuning", "function_calling", "image_input", "predicted_outputs", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 2.5, "_unit": "per 1M tokens", "cached_input": 1.25, "output": 10.0 }, "batch": { "input": 1.25, "_unit": "per 1M tokens", "output": 5.0 }, "fast": { "input": 4.25, "_unit": "per 1M tokens", "cached_input": 2.125, "output": 17.0 }, "model_page:Text tokens": { "Input": { "price": 2.5, "unit": "1M tokens" }, "Cached input": { "price": 1.25, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1739331543, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-audio", "record_kind": "id_only", "canonical_model": "gpt-4o-audio", "display_name": "gpt-4o-audio", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "audio-chat", "status": [ "DEPRECATED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2026-07-20", "shutdown_date": "2027-01-20", "replacement": "`gpt-audio-1.5`", "phase": "upcoming", "section": "2026-07-20: Legacy audio, realtime, and transcription models", "source": "https://developers.openai.com/api/docs/deprecations#2026-07-20-legacy-audio-realtime-and-transcription-models" } ], "shutdown_date": "2027-01-20", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2026-07-20-legacy-audio-realtime-and-transcription-models", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-audio-preview", "record_kind": "model", "canonical_model": "gpt-4o-audio-preview", "display_name": "GPT-4o Audio", "description": "GPT-4o models capable of audio inputs and outputs", "aliases": [], "snapshots": [ "gpt-4o-audio-preview-2025-06-03", "gpt-4o-audio-preview-2024-12-17", "gpt-4o-audio-preview-2024-10-01" ], "default_snapshot": "gpt-4o-audio-preview-2025-06-03", "family": "audio-chat", "status": [ "DOCUMENTED", "RETIRED", "PREVIEW" ], "flags": [], "release_date": "2024-10-17", "release_date_source": "changelog", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" } ], "tools": [], "features_documented": [ "function_calling", "streaming" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 40.0, "unit": "1M tokens" }, "Output": { "price": 80.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 2000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-audio-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2025-09-15", "shutdown_date": "2026-05-07", "replacement": "`gpt-audio-1.5`", "phase": "past", "section": "2025-09-15: `gpt-4o-realtime-preview` models", "source": "https://developers.openai.com/api/docs/deprecations#2025-09-15-gpt-4o-realtime-preview-models" } ], "shutdown_date": "2026-05-07", "intro": "This is a preview release of the GPT-4o Audio models. These models accept audio inputs and outputs, and can be used in the Chat Completions REST API.", "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-audio-preview", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-09-15-gpt-4o-realtime-preview-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-audio-preview-2024-10-01", "record_kind": "snapshot", "canonical_model": "gpt-4o-audio-preview", "display_name": "GPT-4o Audio (snapshot gpt-4o-audio-preview-2024-10-01)", "description": "GPT-4o models capable of audio inputs and outputs", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4o-audio-preview-2025-06-03", "family": "audio-chat", "status": [ "DOCUMENTED", "RETIRED", "PREVIEW" ], "flags": [], "release_date": "2024-10-01", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" } ], "tools": [], "features_documented": [ "function_calling", "streaming" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 40.0, "unit": "1M tokens" }, "Output": { "price": 80.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 2000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-audio-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2025-06-10", "shutdown_date": "2025-10-10", "replacement": "`gpt-audio-1.5`", "phase": "past", "section": "2025-06-10: `gpt-4o-audio-preview-2024-10-01`", "source": "https://developers.openai.com/api/docs/deprecations#2025-06-10-gpt-4o-audio-preview-2024-10-01" } ], "shutdown_date": "2025-10-10", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-audio-preview", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-06-10-gpt-4o-audio-preview-2024-10-01", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-audio-preview-2024-12-17", "record_kind": "snapshot", "canonical_model": "gpt-4o-audio-preview", "display_name": "GPT-4o Audio (snapshot gpt-4o-audio-preview-2024-12-17)", "description": "GPT-4o models capable of audio inputs and outputs", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4o-audio-preview-2025-06-03", "family": "audio-chat", "status": [ "DOCUMENTED", "PREVIEW" ], "flags": [], "release_date": "2024-12-17", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" } ], "tools": [], "features_documented": [ "function_calling", "streaming" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 40.0, "unit": "1M tokens" }, "Output": { "price": 80.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 2000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-audio-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-audio-preview", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-audio-preview-2025-06-03", "record_kind": "snapshot", "canonical_model": "gpt-4o-audio-preview", "display_name": "GPT-4o Audio (snapshot gpt-4o-audio-preview-2025-06-03)", "description": "GPT-4o models capable of audio inputs and outputs", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4o-audio-preview-2025-06-03", "family": "audio-chat", "status": [ "DOCUMENTED", "PREVIEW" ], "flags": [], "release_date": "2025-06-03", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" } ], "tools": [], "features_documented": [ "function_calling", "streaming" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 40.0, "unit": "1M tokens" }, "Output": { "price": 80.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 2000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-audio-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-audio-preview", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-mini", "record_kind": "model", "canonical_model": "gpt-4o-mini", "display_name": "GPT-4o Mini", "description": "Fast, affordable small model for focused tasks", "aliases": [], "snapshots": [ "gpt-4o-mini-2024-07-18" ], "default_snapshot": "gpt-4o-mini-2024-07-18", "family": "gpt-4o", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2024-07-18", "release_date_source": "changelog", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": true, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "file_search", "file_uploads", "fine_tuning", "function_calling", "image_input", "predicted_outputs", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 0.15, "_unit": "per 1M tokens", "cached_input": 0.075, "output": 0.6 }, "batch": { "input": 0.075, "_unit": "per 1M tokens", "output": 0.3 }, "fast": { "input": 0.25, "_unit": "per 1M tokens", "cached_input": 0.125, "output": 1.0 }, "model_page:Text tokens": { "Input": { "price": 0.15, "unit": "1M tokens" }, "Cached input": { "price": 0.075, "unit": "1M tokens" }, "Output": { "price": 0.6, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 2000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "RPD": null, "TPM": 150000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1721172741, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-4o Mini (“o” for “omni”) is a fast, affordable small model for focused tasks. It accepts both text and image inputs, and produces text outputs (including Structured Outputs). It is ideal for fine-tuning, and model outputs from a larger model like GPT-4o can be distilled to GPT-4o-Mini to produce similar results at lower cost and latency.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-mini", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-mini-2024-07-18", "record_kind": "snapshot", "canonical_model": "gpt-4o-mini", "display_name": "GPT-4o Mini (snapshot gpt-4o-mini-2024-07-18)", "description": "Fast, affordable small model for focused tasks", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4o-mini-2024-07-18", "family": "gpt-4o", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2024-07-18", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": true, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "file_search", "file_uploads", "fine_tuning", "function_calling", "image_input", "predicted_outputs", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 0.15, "_unit": "per 1M tokens", "cached_input": 0.075, "output": 0.6 }, "batch": { "input": 0.075, "_unit": "per 1M tokens", "output": 0.3 }, "fast": { "input": 0.25, "_unit": "per 1M tokens", "cached_input": 0.125, "output": 1.0 }, "model_page:Text tokens": { "Input": { "price": 0.15, "unit": "1M tokens" }, "Cached input": { "price": 0.075, "unit": "1M tokens" }, "Output": { "price": 0.6, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 2000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "RPD": null, "TPM": 150000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1721172717, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-mini", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-mini-audio", "record_kind": "id_only", "canonical_model": "gpt-4o-mini-audio", "display_name": "gpt-4o-mini-audio", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "audio-chat", "status": [ "DEPRECATED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2026-07-20", "shutdown_date": "2027-01-20", "replacement": "`gpt-audio-1.5`", "phase": "upcoming", "section": "2026-07-20: Legacy audio, realtime, and transcription models", "source": "https://developers.openai.com/api/docs/deprecations#2026-07-20-legacy-audio-realtime-and-transcription-models" } ], "shutdown_date": "2027-01-20", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2026-07-20-legacy-audio-realtime-and-transcription-models", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-mini-audio-preview", "record_kind": "model", "canonical_model": "gpt-4o-mini-audio-preview", "display_name": "GPT-4o Mini Audio", "description": "Smaller model capable of audio inputs and outputs", "aliases": [], "snapshots": [ "gpt-4o-mini-audio-preview-2024-12-17" ], "default_snapshot": "gpt-4o-mini-audio-preview-2024-12-17", "family": "audio-chat", "status": [ "DOCUMENTED", "RETIRED", "PREVIEW" ], "flags": [], "release_date": "2024-12-17", "release_date_source": "changelog", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": false, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" } ], "tools": [ "code_interpreter", "file_search", "mcp", "web_search" ], "features_documented": [ "function_calling", "streaming" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 0.15, "unit": "1M tokens" }, "Output": { "price": 0.6, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 10.0, "unit": "1M tokens" }, "Output": { "price": 20.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "free": { "RPM": 3, "RPD": 200, "TPM": 40000, "Batch queue limit": null }, "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 2000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "RPD": null, "TPM": 150000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-audio-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2025-09-15", "shutdown_date": "2026-05-07", "replacement": "`gpt-audio-mini`", "phase": "past", "section": "2025-09-15: `gpt-4o-realtime-preview` models", "source": "https://developers.openai.com/api/docs/deprecations#2025-09-15-gpt-4o-realtime-preview-models" } ], "shutdown_date": "2026-05-07", "intro": "This is a preview release of the smaller GPT-4o Audio Mini model. It's designed to input audio or create audio outputs via the REST API.", "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-mini-audio-preview", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-09-15-gpt-4o-realtime-preview-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-mini-audio-preview-2024-12-17", "record_kind": "snapshot", "canonical_model": "gpt-4o-mini-audio-preview", "display_name": "GPT-4o Mini Audio (snapshot gpt-4o-mini-audio-preview-2024-12-17)", "description": "Smaller model capable of audio inputs and outputs", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4o-mini-audio-preview-2024-12-17", "family": "audio-chat", "status": [ "DOCUMENTED", "PREVIEW" ], "flags": [], "release_date": "2024-12-17", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": false, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" } ], "tools": [ "code_interpreter", "file_search", "mcp", "web_search" ], "features_documented": [ "function_calling", "streaming" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 0.15, "unit": "1M tokens" }, "Output": { "price": 0.6, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 10.0, "unit": "1M tokens" }, "Output": { "price": 20.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "free": { "RPM": 3, "RPD": 200, "TPM": 40000, "Batch queue limit": null }, "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 2000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "RPD": null, "TPM": 150000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-audio-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-mini-audio-preview", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-mini-realtime", "record_kind": "id_only", "canonical_model": "gpt-4o-mini-realtime", "display_name": "gpt-4o-mini-realtime", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "realtime", "status": [ "DEPRECATED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2026-07-20", "shutdown_date": "2027-01-20", "replacement": "`gpt-realtime-2.1-mini`", "phase": "upcoming", "section": "2026-07-20: Legacy audio, realtime, and transcription models", "source": "https://developers.openai.com/api/docs/deprecations#2026-07-20-legacy-audio-realtime-and-transcription-models" } ], "shutdown_date": "2027-01-20", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2026-07-20-legacy-audio-realtime-and-transcription-models", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-mini-realtime-preview", "record_kind": "model", "canonical_model": "gpt-4o-mini-realtime-preview", "display_name": "GPT-4o Mini Realtime", "description": "Smaller realtime model for text and audio inputs and outputs", "aliases": [], "snapshots": [ "gpt-4o-mini-realtime-preview-2024-12-17" ], "default_snapshot": "gpt-4o-mini-realtime-preview-2024-12-17", "family": "realtime", "status": [ "DOCUMENTED", "RETIRED", "PREVIEW" ], "flags": [], "release_date": "2024-12-17", "release_date_source": "changelog", "knowledge_cutoff": "2023-10-01", "context_window": 16000, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": true, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Realtime", "route": "/v1/realtime" } ], "tools": [], "features_documented": [ "function_calling", "prompt_caching" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 0.6, "unit": "1M tokens" }, "Cached input": { "price": 0.3, "unit": "1M tokens" }, "Output": { "price": 2.4, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 10.0, "unit": "1M tokens" }, "Cached input": { "price": 0.3, "unit": "1M tokens" }, "Output": { "price": 20.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 200, "RPD": 1000, "TPM": 40000 }, "Tier 2": { "RPM": 400, "RPD": null, "TPM": 200000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 800000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 4000000 }, "Tier 5": { "RPM": 20000, "RPD": null, "TPM": 15000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-realtime-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2025-09-15", "shutdown_date": "2026-05-07", "replacement": "`gpt-realtime-mini`", "phase": "past", "section": "2025-09-15: `gpt-4o-realtime-preview` models", "source": "https://developers.openai.com/api/docs/deprecations#2025-09-15-gpt-4o-realtime-preview-models" } ], "shutdown_date": "2026-05-07", "intro": "This is a preview release of the GPT-4o-Mini Realtime model, capable of responding to audio and text inputs in realtime over WebRTC or a WebSocket interface.", "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-mini-realtime-preview", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-09-15-gpt-4o-realtime-preview-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-mini-realtime-preview-2024-12-17", "record_kind": "snapshot", "canonical_model": "gpt-4o-mini-realtime-preview", "display_name": "GPT-4o Mini Realtime (snapshot gpt-4o-mini-realtime-preview-2024-12-17)", "description": "Smaller realtime model for text and audio inputs and outputs", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4o-mini-realtime-preview-2024-12-17", "family": "realtime", "status": [ "DOCUMENTED", "PREVIEW" ], "flags": [], "release_date": "2024-12-17", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 16000, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": true, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Realtime", "route": "/v1/realtime" } ], "tools": [], "features_documented": [ "function_calling", "prompt_caching" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 0.6, "unit": "1M tokens" }, "Cached input": { "price": 0.3, "unit": "1M tokens" }, "Output": { "price": 2.4, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 10.0, "unit": "1M tokens" }, "Cached input": { "price": 0.3, "unit": "1M tokens" }, "Output": { "price": 20.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 200, "RPD": 1000, "TPM": 40000 }, "Tier 2": { "RPM": 400, "RPD": null, "TPM": 200000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 800000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 4000000 }, "Tier 5": { "RPM": 20000, "RPD": null, "TPM": 15000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-realtime-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-mini-realtime-preview", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-mini-search-preview", "record_kind": "model", "canonical_model": "gpt-4o-mini-search-preview", "display_name": "GPT-4o Mini Search Preview", "description": "Fast, affordable small model for web search", "aliases": [], "snapshots": [ "gpt-4o-mini-search-preview-2025-03-11" ], "default_snapshot": "gpt-4o-mini-search-preview-2025-03-11", "family": "search", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "PREVIEW" ], "flags": [], "release_date": "2025-03-11", "release_date_source": "changelog", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" } ], "tools": [], "features_documented": [ "image_input", "streaming", "structured_outputs" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 0.15, "unit": "1M tokens" }, "Output": { "price": 0.6, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "free": { "RPM": 3, "RPD": 200, "TPM": 40000, "Batch queue limit": null }, "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 2000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "RPD": null, "TPM": 150000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-search-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1741391161, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-4o Mini Search Preview is a specialized model trained to understand and execute [web search](/api/docs/guides/tools-web-search?api-mode=chat) queries with the Chat Completions API. In addition to token fees, web search queries have a fee per tool call. Learn more in the [pricing](/api/docs/pricing) page.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-mini-search-preview", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-mini-search-preview-2025-03-11", "record_kind": "snapshot", "canonical_model": "gpt-4o-mini-search-preview", "display_name": "GPT-4o Mini Search Preview (snapshot gpt-4o-mini-search-preview-2025-03-11)", "description": "Fast, affordable small model for web search", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4o-mini-search-preview-2025-03-11", "family": "search", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "RETIRED", "PREVIEW" ], "flags": [ "STILL_LISTED_AFTER_DOCUMENTED_SHUTDOWN" ], "release_date": "2025-03-11", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" } ], "tools": [], "features_documented": [ "image_input", "streaming", "structured_outputs" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 0.15, "unit": "1M tokens" }, "Output": { "price": 0.6, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "free": { "RPM": 3, "RPD": 200, "TPM": 40000, "Batch queue limit": null }, "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 2000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "RPD": null, "TPM": 150000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-search-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1741390858, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-07-23", "replacement": "`gpt-5.6-terra`", "phase": "past", "section": "2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown" }, { "announced": null, "shutdown_date": "2026-07-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-07-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-mini-search-preview", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-mini-transcribe", "record_kind": "model", "canonical_model": "gpt-4o-mini-transcribe", "display_name": "GPT-4o Mini Transcribe", "description": "Speech-to-text model powered by GPT-4o Mini", "aliases": [], "snapshots": [ "gpt-4o-mini-transcribe-2025-03-20", "gpt-4o-mini-transcribe-2025-12-15" ], "default_snapshot": "gpt-4o-mini-transcribe-2025-12-15", "family": "speech-to-text", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-03-20", "release_date_source": "changelog", "knowledge_cutoff": "2024-06-01", "context_window": 16000, "max_input": null, "max_output": 2000, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": true, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": true, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Realtime", "route": "/v1/realtime" }, { "name": "Transcription", "route": "/v1/audio/transcriptions" } ], "tools": [], "features_documented": [], "pricing": { "standard": { "audio_input": 1.25, "_unit": "per 1M tokens", "text_output": 5.0, "audio_duration": 0.003 }, "model_page:Audio tokens": { "Input": { "price": 1.25, "unit": "1M tokens" }, "Output": { "price": 5.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 50000 }, "Tier 2": { "RPM": 2000, "TPM": 150000 }, "Tier 3": { "RPM": 5000, "TPM": 600000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000 }, "Tier 5": { "RPM": 10000, "TPM": 8000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-transcribe", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1742068596, "openapi_enum": true }, "deprecation": [ { "announced": "2026-08-26", "shutdown_date": "2027-02-26", "replacement": "`gpt-live-transcribe` or `gpt-transcribe`", "phase": "upcoming", "section": "2026-08-26: Transcription models", "source": "https://developers.openai.com/api/docs/deprecations#2026-08-26-transcription-models" }, { "announced": null, "shutdown_date": "2027-02-26", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2027-02-26", "intro": "GPT-4o Mini Transcribe is a speech-to-text model that uses GPT-4o Mini to transcribe audio. It offers improvements to word error rate and better language recognition and accuracy compared to original Whisper models. Use it for more accurate transcripts.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-mini-transcribe", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-08-26-transcription-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-mini-transcribe-2025-03-20", "record_kind": "snapshot", "canonical_model": "gpt-4o-mini-transcribe", "display_name": "GPT-4o Mini Transcribe (snapshot gpt-4o-mini-transcribe-2025-03-20)", "description": "Speech-to-text model powered by GPT-4o Mini", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4o-mini-transcribe-2025-12-15", "family": "speech-to-text", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-03-20", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2024-06-01", "context_window": 16000, "max_input": null, "max_output": 2000, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": true, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": true, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Realtime", "route": "/v1/realtime" }, { "name": "Transcription", "route": "/v1/audio/transcriptions" } ], "tools": [], "features_documented": [], "pricing": { "standard": { "audio_input": 1.25, "_unit": "per 1M tokens", "text_output": 5.0, "audio_duration": 0.003 }, "model_page:Audio tokens": { "Input": { "price": 1.25, "unit": "1M tokens" }, "Output": { "price": 5.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 50000 }, "Tier 2": { "RPM": 2000, "TPM": 150000 }, "Tier 3": { "RPM": 5000, "TPM": 600000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000 }, "Tier 5": { "RPM": 10000, "TPM": 8000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-transcribe", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1765610545, "openapi_enum": false }, "deprecation": [ { "announced": "2026-07-20", "shutdown_date": "2027-01-20", "replacement": "`gpt-4o-mini-transcribe-2025-12-15`", "phase": "upcoming", "section": "2026-07-20: Legacy audio, realtime, and transcription models", "source": "https://developers.openai.com/api/docs/deprecations#2026-07-20-legacy-audio-realtime-and-transcription-models" }, { "announced": null, "shutdown_date": "2027-01-20", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2027-01-20", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-mini-transcribe", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-07-20-legacy-audio-realtime-and-transcription-models", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-mini-transcribe-2025-12-15", "record_kind": "snapshot", "canonical_model": "gpt-4o-mini-transcribe", "display_name": "GPT-4o Mini Transcribe (snapshot gpt-4o-mini-transcribe-2025-12-15)", "description": "Speech-to-text model powered by GPT-4o Mini", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4o-mini-transcribe-2025-12-15", "family": "speech-to-text", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-12-15", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2024-06-01", "context_window": 16000, "max_input": null, "max_output": 2000, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": true, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": true, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Realtime", "route": "/v1/realtime" }, { "name": "Transcription", "route": "/v1/audio/transcriptions" } ], "tools": [], "features_documented": [], "pricing": { "standard": { "audio_input": 1.25, "_unit": "per 1M tokens", "text_output": 5.0, "audio_duration": 0.003 }, "model_page:Audio tokens": { "Input": { "price": 1.25, "unit": "1M tokens" }, "Output": { "price": 5.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 50000 }, "Tier 2": { "RPM": 2000, "TPM": 150000 }, "Tier 3": { "RPM": 5000, "TPM": 600000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000 }, "Tier 5": { "RPM": 10000, "TPM": 8000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-transcribe", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1765610407, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-mini-transcribe", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-mini-tts", "record_kind": "model", "canonical_model": "gpt-4o-mini-tts", "display_name": "GPT-4o Mini TTS", "description": "Text-to-speech model powered by GPT-4o Mini", "aliases": [], "snapshots": [ "gpt-4o-mini-tts-2025-03-20", "gpt-4o-mini-tts-2025-12-15" ], "default_snapshot": "gpt-4o-mini-tts-2025-12-15", "family": "text-to-speech", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-03-20", "release_date_source": "changelog", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text" ], "output": [ "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": false, "image_in": false, "image_out": false, "audio_in": false, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": true, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Speech generation", "route": "/v1/audio/speech" } ], "tools": [], "features_documented": [], "pricing": { "standard": { "audio_output": 12.0, "_unit": "per 1M tokens", "text_input": 0.6 }, "model_page:Text tokens": { "Input": { "price": 0.6, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Output": { "price": 12.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 50000 }, "Tier 2": { "RPM": 2000, "TPM": 150000 }, "Tier 3": { "RPM": 5000, "TPM": 600000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000 }, "Tier 5": { "RPM": 10000, "TPM": 8000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-tts", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1742403959, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-4o Mini TTS is a text-to-speech model built on GPT-4o Mini, a fast and powerful language model. Use it to convert text to natural sounding spoken text. The maximum number of input tokens is 2000.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-mini-tts", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-mini-tts-2025-03-20", "record_kind": "snapshot", "canonical_model": "gpt-4o-mini-tts", "display_name": "GPT-4o Mini TTS (snapshot gpt-4o-mini-tts-2025-03-20)", "description": "Text-to-speech model powered by GPT-4o Mini", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4o-mini-tts-2025-12-15", "family": "text-to-speech", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "RETIRED" ], "flags": [ "STILL_LISTED_AFTER_DOCUMENTED_SHUTDOWN", "SHUTDOWN_DATE_ONLY_IN_LIVE_API" ], "release_date": "2025-03-20", "release_date_source": "snapshot date in id", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text" ], "output": [ "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": false, "image_in": false, "image_out": false, "audio_in": false, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": true, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Speech generation", "route": "/v1/audio/speech" } ], "tools": [], "features_documented": [], "pricing": { "standard": { "audio_output": 12.0, "_unit": "per 1M tokens", "text_input": 0.6 }, "model_page:Text tokens": { "Input": { "price": 0.6, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Output": { "price": 12.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 50000 }, "Tier 2": { "RPM": 2000, "TPM": 150000 }, "Tier 3": { "RPM": 5000, "TPM": 600000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000 }, "Tier 5": { "RPM": 10000, "TPM": 8000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-tts", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1765610731, "openapi_enum": false }, "deprecation": [ { "announced": null, "shutdown_date": "2026-07-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-07-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-mini-tts", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-mini-tts-2025-12-15", "record_kind": "snapshot", "canonical_model": "gpt-4o-mini-tts", "display_name": "GPT-4o Mini TTS (snapshot gpt-4o-mini-tts-2025-12-15)", "description": "Text-to-speech model powered by GPT-4o Mini", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4o-mini-tts-2025-12-15", "family": "text-to-speech", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-12-15", "release_date_source": "snapshot date in id", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text" ], "output": [ "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": false, "image_in": false, "image_out": false, "audio_in": false, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": true, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Speech generation", "route": "/v1/audio/speech" } ], "tools": [], "features_documented": [], "pricing": { "standard": { "audio_output": 12.0, "_unit": "per 1M tokens", "text_input": 0.6 }, "model_page:Text tokens": { "Input": { "price": 0.6, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Output": { "price": 12.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 50000 }, "Tier 2": { "RPM": 2000, "TPM": 150000 }, "Tier 3": { "RPM": 5000, "TPM": 600000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000 }, "Tier 5": { "RPM": 10000, "TPM": 8000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-tts", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1765610837, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-mini-tts", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-realtime", "record_kind": "id_only", "canonical_model": "gpt-4o-realtime", "display_name": "gpt-4o-realtime", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "realtime", "status": [ "DEPRECATED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2026-07-20", "shutdown_date": "2027-01-20", "replacement": "`gpt-realtime-2.1`", "phase": "upcoming", "section": "2026-07-20: Legacy audio, realtime, and transcription models", "source": "https://developers.openai.com/api/docs/deprecations#2026-07-20-legacy-audio-realtime-and-transcription-models" } ], "shutdown_date": "2027-01-20", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2026-07-20-legacy-audio-realtime-and-transcription-models", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-realtime-preview", "record_kind": "model", "canonical_model": "gpt-4o-realtime-preview", "display_name": "GPT-4o Realtime", "description": "Model capable of realtime text and audio inputs and outputs", "aliases": [], "snapshots": [ "gpt-4o-realtime-preview-2025-06-03", "gpt-4o-realtime-preview-2024-12-17", "gpt-4o-realtime-preview-2024-10-01" ], "default_snapshot": "gpt-4o-realtime-preview-2025-06-03", "family": "realtime", "status": [ "DOCUMENTED", "RETIRED", "PREVIEW" ], "flags": [], "release_date": "2024-10-01", "release_date_source": "changelog", "knowledge_cutoff": "2023-10-01", "context_window": 32000, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": true, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Realtime", "route": "/v1/realtime" } ], "tools": [], "features_documented": [ "function_calling", "prompt_caching" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Cached input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 20.0, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 40.0, "unit": "1M tokens" }, "Cached input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 80.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 200, "RPD": 1000, "TPM": 40000 }, "Tier 2": { "RPM": 400, "RPD": null, "TPM": 200000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 800000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 4000000 }, "Tier 5": { "RPM": 20000, "RPD": null, "TPM": 15000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-realtime-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2025-09-15", "shutdown_date": "2026-05-07", "replacement": "`gpt-realtime-1.5`", "phase": "past", "section": "2025-09-15: `gpt-4o-realtime-preview` models", "source": "https://developers.openai.com/api/docs/deprecations#2025-09-15-gpt-4o-realtime-preview-models" } ], "shutdown_date": "2026-05-07", "intro": "This is a preview release of the GPT-4o Realtime model, capable of responding to audio and text inputs in realtime over WebRTC or a WebSocket interface.", "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-realtime-preview", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-09-15-gpt-4o-realtime-preview-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-realtime-preview-2024-10-01", "record_kind": "snapshot", "canonical_model": "gpt-4o-realtime-preview", "display_name": "GPT-4o Realtime (snapshot gpt-4o-realtime-preview-2024-10-01)", "description": "Model capable of realtime text and audio inputs and outputs", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4o-realtime-preview-2025-06-03", "family": "realtime", "status": [ "DOCUMENTED", "RETIRED", "PREVIEW" ], "flags": [], "release_date": "2024-10-01", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 32000, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": true, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Realtime", "route": "/v1/realtime" } ], "tools": [], "features_documented": [ "function_calling", "prompt_caching" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Cached input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 20.0, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 40.0, "unit": "1M tokens" }, "Cached input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 80.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 200, "RPD": 1000, "TPM": 40000 }, "Tier 2": { "RPM": 400, "RPD": null, "TPM": 200000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 800000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 4000000 }, "Tier 5": { "RPM": 20000, "RPD": null, "TPM": 15000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-realtime-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2025-06-10", "shutdown_date": "2025-10-10", "replacement": "`gpt-realtime-1.5`", "phase": "past", "section": "2025-06-10: `gpt-4o-realtime-preview-2024-10-01`", "source": "https://developers.openai.com/api/docs/deprecations#2025-06-10-gpt-4o-realtime-preview-2024-10-01" } ], "shutdown_date": "2025-10-10", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-realtime-preview", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-06-10-gpt-4o-realtime-preview-2024-10-01", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-realtime-preview-2024-12-17", "record_kind": "snapshot", "canonical_model": "gpt-4o-realtime-preview", "display_name": "GPT-4o Realtime (snapshot gpt-4o-realtime-preview-2024-12-17)", "description": "Model capable of realtime text and audio inputs and outputs", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4o-realtime-preview-2025-06-03", "family": "realtime", "status": [ "DOCUMENTED", "RETIRED", "PREVIEW" ], "flags": [], "release_date": "2024-12-17", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 32000, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": true, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Realtime", "route": "/v1/realtime" } ], "tools": [], "features_documented": [ "function_calling", "prompt_caching" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Cached input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 20.0, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 40.0, "unit": "1M tokens" }, "Cached input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 80.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 200, "RPD": 1000, "TPM": 40000 }, "Tier 2": { "RPM": 400, "RPD": null, "TPM": 200000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 800000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 4000000 }, "Tier 5": { "RPM": 20000, "RPD": null, "TPM": 15000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-realtime-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2025-09-15", "shutdown_date": "2026-05-07", "replacement": "`gpt-realtime-1.5`", "phase": "past", "section": "2025-09-15: `gpt-4o-realtime-preview` models", "source": "https://developers.openai.com/api/docs/deprecations#2025-09-15-gpt-4o-realtime-preview-models" } ], "shutdown_date": "2026-05-07", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-realtime-preview", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-09-15-gpt-4o-realtime-preview-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-realtime-preview-2025-06-03", "record_kind": "snapshot", "canonical_model": "gpt-4o-realtime-preview", "display_name": "GPT-4o Realtime (snapshot gpt-4o-realtime-preview-2025-06-03)", "description": "Model capable of realtime text and audio inputs and outputs", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4o-realtime-preview-2025-06-03", "family": "realtime", "status": [ "DOCUMENTED", "RETIRED", "PREVIEW" ], "flags": [], "release_date": "2025-06-03", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 32000, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": true, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Realtime", "route": "/v1/realtime" } ], "tools": [], "features_documented": [ "function_calling", "prompt_caching" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Cached input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 20.0, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 40.0, "unit": "1M tokens" }, "Cached input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 80.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 200, "RPD": 1000, "TPM": 40000 }, "Tier 2": { "RPM": 400, "RPD": null, "TPM": 200000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 800000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 4000000 }, "Tier 5": { "RPM": 20000, "RPD": null, "TPM": 15000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-realtime-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2025-09-15", "shutdown_date": "2026-05-07", "replacement": "`gpt-realtime-1.5`", "phase": "past", "section": "2025-09-15: `gpt-4o-realtime-preview` models", "source": "https://developers.openai.com/api/docs/deprecations#2025-09-15-gpt-4o-realtime-preview-models" } ], "shutdown_date": "2026-05-07", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-realtime-preview", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-09-15-gpt-4o-realtime-preview-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-search-preview", "record_kind": "model", "canonical_model": "gpt-4o-search-preview", "display_name": "GPT-4o Search Preview", "description": "GPT model for web search in Chat Completions", "aliases": [], "snapshots": [ "gpt-4o-search-preview-2025-03-11" ], "default_snapshot": "gpt-4o-search-preview-2025-03-11", "family": "search", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "PREVIEW" ], "flags": [], "release_date": "2025-03-11", "release_date_source": "changelog", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" } ], "tools": [], "features_documented": [ "image_input", "streaming", "structured_outputs" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 100, "TPM": 30000, "Batch queue limit": 0 }, "Tier 2": { "RPM": 500, "TPM": 45000, "Batch queue limit": 0 }, "Tier 3": { "RPM": 500, "TPM": 80000, "Batch queue limit": 0 }, "Tier 4": { "RPM": 1000, "TPM": 200000, "Batch queue limit": 0 }, "Tier 5": { "RPM": 1000, "TPM": 3000000, "Batch queue limit": 0 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-search-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1771905534, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-4o Search Preview is a specialized model trained to understand and execute [web search](/api/docs/guides/tools-web-search?api-mode=chat) queries with the Chat Completions API. In addition to token fees, web search queries have a fee per tool call. Learn more in the [pricing](/api/docs/pricing) page.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-search-preview", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-search-preview-2025-03-11", "record_kind": "snapshot", "canonical_model": "gpt-4o-search-preview", "display_name": "GPT-4o Search Preview (snapshot gpt-4o-search-preview-2025-03-11)", "description": "GPT model for web search in Chat Completions", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4o-search-preview-2025-03-11", "family": "search", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "RETIRED", "PREVIEW" ], "flags": [ "STILL_LISTED_AFTER_DOCUMENTED_SHUTDOWN" ], "release_date": "2025-03-11", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" } ], "tools": [], "features_documented": [ "image_input", "streaming", "structured_outputs" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 100, "TPM": 30000, "Batch queue limit": 0 }, "Tier 2": { "RPM": 500, "TPM": 45000, "Batch queue limit": 0 }, "Tier 3": { "RPM": 500, "TPM": 80000, "Batch queue limit": 0 }, "Tier 4": { "RPM": 1000, "TPM": 200000, "Batch queue limit": 0 }, "Tier 5": { "RPM": 1000, "TPM": 3000000, "Batch queue limit": 0 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-search-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1771905621, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-07-23", "replacement": "`gpt-5.6-terra`", "phase": "past", "section": "2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown" }, { "announced": null, "shutdown_date": "2026-07-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-07-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-search-preview", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-transcribe", "record_kind": "model", "canonical_model": "gpt-4o-transcribe", "display_name": "GPT-4o Transcribe", "description": "Speech-to-text model powered by GPT-4o", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4o-transcribe", "family": "speech-to-text", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-03-20", "release_date_source": "changelog", "knowledge_cutoff": "2024-06-01", "context_window": 16000, "max_input": null, "max_output": 2000, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": true, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": true, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Realtime", "route": "/v1/realtime" }, { "name": "Transcription", "route": "/v1/audio/transcriptions" } ], "tools": [], "features_documented": [], "pricing": { "standard": { "audio_input": 2.5, "_unit": "per 1M tokens", "text_output": 10.0, "audio_duration": 0.006 }, "model_page:Audio tokens": { "Input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 10000 }, "Tier 2": { "RPM": 2000, "TPM": 100000 }, "Tier 3": { "RPM": 5000, "TPM": 400000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000 }, "Tier 5": { "RPM": 10000, "TPM": 6000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-transcribe", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1742068463, "openapi_enum": true }, "deprecation": [ { "announced": "2026-08-26", "shutdown_date": "2027-02-26", "replacement": "`gpt-live-transcribe` or `gpt-transcribe`", "phase": "upcoming", "section": "2026-08-26: Transcription models", "source": "https://developers.openai.com/api/docs/deprecations#2026-08-26-transcription-models" }, { "announced": null, "shutdown_date": "2027-02-26", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2027-02-26", "intro": "GPT-4o Transcribe is a speech-to-text model that uses GPT-4o to transcribe audio. It offers improvements to word error rate and better language recognition and accuracy compared to original Whisper models. Use it for more accurate transcripts.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-transcribe", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-08-26-transcription-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-4o-transcribe-diarize", "record_kind": "model", "canonical_model": "gpt-4o-transcribe-diarize", "display_name": "GPT-4o Transcribe Diarize", "description": "Transcription model that identifies who's speaking when", "aliases": [], "snapshots": [], "default_snapshot": "gpt-4o-transcribe-diarize", "family": "speech-to-text", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-06-24", "release_date_source": "GET /v1/models created timestamp (approximation)", "knowledge_cutoff": "2024-06-01", "context_window": 16000, "max_input": null, "max_output": 2000, "modalities": { "input": [ "text", "audio" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": true, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Transcription", "route": "/v1/audio/transcriptions" } ], "tools": [], "features_documented": [], "pricing": { "standard": { "audio_input": 2.5, "_unit": "per 1M tokens", "text_output": 10.0, "audio_duration": 0.006 }, "model_page:Audio tokens": { "Input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 10000 }, "Tier 2": { "RPM": 5000, "TPM": 100000 }, "Tier 3": { "RPM": 5000, "TPM": 400000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000 }, "Tier 5": { "RPM": 10000, "TPM": 6000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-4o-transcribe-diarize", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1750798887, "openapi_enum": true }, "deprecation": [ { "announced": "2026-08-26", "shutdown_date": "2027-02-26", "replacement": "`gpt-live-transcribe` or `gpt-transcribe`", "phase": "upcoming", "section": "2026-08-26: Transcription models", "source": "https://developers.openai.com/api/docs/deprecations#2026-08-26-transcription-models" }, { "announced": null, "shutdown_date": "2027-02-26", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2027-02-26", "intro": "GPT-4o Transcribe Diarize is an automatic speech recognition (ASR) model with built-in speaker diarization, meaning it associates audio segments with different speakers in a conversation. This model is only available in the Transcription API.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-4o-transcribe-diarize", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-08-26-transcription-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5", "record_kind": "model", "canonical_model": "gpt-5", "display_name": "GPT-5", "description": "Previous intelligent reasoning model for coding and agentic tasks with configurable reasoning effort", "aliases": [], "snapshots": [ "gpt-5-2025-08-07" ], "default_snapshot": "gpt-5-2025-08-07", "family": "gpt-5", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-08-07", "release_date_source": "changelog", "knowledge_cutoff": "2024-09-30", "context_window": 400000, "max_input": 272000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "minimal", "low", "medium", "high" ], "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 1.25, "_unit": "per 1M tokens", "cached_input": 0.125, "output": 10.0 }, "batch": { "input": 0.625, "_unit": "per 1M tokens", "cached_input": 0.0625, "output": 5.0 }, "flex": { "input": 0.625, "_unit": "per 1M tokens", "cached_input": 0.0625, "output": 5.0 }, "fast": { "input": 2.5, "_unit": "per 1M tokens", "cached_input": 0.25, "output": 20.0 }, "model_page:Text tokens": { "Input": { "price": 1.25, "unit": "1M tokens" }, "Cached input": { "price": 0.125, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1754425777, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-5 is our previous model for coding, reasoning, and agentic tasks across domains. We recommend using the latest [GPT-6 Astra](/api/docs/models/gpt-6-astra). Learn more on the [Model guidance](/api/docs/guides/latest-model) page. Reasoning.effort supports: minimal, low, medium, and high.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5-2025-08-07", "record_kind": "snapshot", "canonical_model": "gpt-5", "display_name": "GPT-5 (snapshot gpt-5-2025-08-07)", "description": "Previous intelligent reasoning model for coding and agentic tasks with configurable reasoning effort", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5-2025-08-07", "family": "gpt-5", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-08-07", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2024-09-30", "context_window": 400000, "max_input": 272000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "minimal", "low", "medium", "high" ], "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 1.25, "_unit": "per 1M tokens", "cached_input": 0.125, "output": 10.0 }, "batch": { "input": 0.625, "_unit": "per 1M tokens", "cached_input": 0.0625, "output": 5.0 }, "flex": { "input": 0.625, "_unit": "per 1M tokens", "cached_input": 0.0625, "output": 5.0 }, "fast": { "input": 2.5, "_unit": "per 1M tokens", "cached_input": 0.25, "output": 20.0 }, "model_page:Text tokens": { "Input": { "price": 1.25, "unit": "1M tokens" }, "Cached input": { "price": 0.125, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1754075360, "openapi_enum": true }, "deprecation": [ { "announced": "2026-06-11", "shutdown_date": "2026-12-11", "replacement": "`gpt-5.6-sol`", "phase": "upcoming", "section": "2026-06-11: GPT-5 and o3 model deprecations", "source": "https://developers.openai.com/api/docs/deprecations#2026-06-11-gpt-5-and-o3-model-deprecations" }, { "announced": null, "shutdown_date": "2026-12-11", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-12-11", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-06-11-gpt-5-and-o3-model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5-chat-latest", "record_kind": "model", "canonical_model": "gpt-5-chat-latest", "display_name": "GPT-5 Chat", "description": "GPT-5 model used in ChatGPT", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5-chat-latest", "family": "chatgpt-latest", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "RETIRED" ], "flags": [ "STILL_LISTED_AFTER_DOCUMENTED_SHUTDOWN" ], "release_date": "2025-08-07", "release_date_source": "changelog", "knowledge_cutoff": "2024-09-30", "context_window": 128000, "max_input": 272000, "max_output": 16384, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "function_calling", "image_input", "streaming", "structured_outputs" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 1.25, "unit": "1M tokens" }, "Cached input": { "price": 0.125, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 50000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5-chat-latest", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1754073306, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-07-23", "replacement": "`gpt-5.6-sol`", "phase": "past", "section": "2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown" }, { "announced": null, "shutdown_date": "2026-07-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-07-23", "intro": "GPT-5 Chat points to the GPT-5 snapshot previously used in ChatGPT. For the latest Chat model, please refer to our [models page](/api/docs/models). We recommend using our [Model guidance](https://developers.openai.com/api/docs/guides/latest-model) for most API usage.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5-chat-latest", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5-codex", "record_kind": "model", "canonical_model": "gpt-5-codex", "display_name": "GPT-5-Codex", "description": "A version of GPT-5 optimized for agentic coding in Codex", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5-codex", "family": "codex", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "RETIRED" ], "flags": [ "STILL_LISTED_AFTER_DOCUMENTED_SHUTDOWN" ], "release_date": "2025-09-23", "release_date_source": "changelog", "knowledge_cutoff": "2024-09-30", "context_window": 400000, "max_input": 272000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" } ], "tools": [ "function_calling", "web_search" ], "features_documented": [ "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 1.25, "unit": "1M tokens" }, "Cached input": { "price": 0.125, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 10000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5-codex", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1757527818, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-07-23", "replacement": "`gpt-5.6-sol`", "phase": "past", "section": "2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown" }, { "announced": null, "shutdown_date": "2026-07-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-07-23", "intro": "GPT-5-Codex is a version of GPT-5 optimized for agentic coding tasks in [Codex](https://developers.openai.com/codex) or similar environments. It's available in the [Responses API](/api/docs/api-reference/responses) only and the underlying model snapshot will be regularly updated. If you want to learn more about prompting GPT-5-Codex, refer to our [dedicated guide](/cookbook/examples/gpt-5/codex_prompting_guide).", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models/gpt-5-codex -> 200", "get_model": { "status": 200, "id": "gpt-5-codex", "object": "model", "created": 1757527818, "owned_by": "system", "shutdown_date": "2026-07-23" } }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5-codex", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5-mini", "record_kind": "model", "canonical_model": "gpt-5-mini", "display_name": "GPT-5 Mini", "description": "Strong intelligence for cost sensitive, low latency, high volume workloads", "aliases": [], "snapshots": [ "gpt-5-mini-2025-08-07" ], "default_snapshot": "gpt-5-mini-2025-08-07", "family": "gpt-5", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-08-07", "release_date_source": "changelog", "knowledge_cutoff": "2024-05-31", "context_window": 400000, "max_input": 272000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": false, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "mcp", "web_search" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 0.25, "_unit": "per 1M tokens", "cached_input": 0.025, "output": 2.0 }, "batch": { "input": 0.125, "_unit": "per 1M tokens", "cached_input": 0.0125, "output": 1.0 }, "flex": { "input": 0.125, "_unit": "per 1M tokens", "cached_input": 0.0125, "output": 1.0 }, "fast": { "input": 0.45, "_unit": "per 1M tokens", "cached_input": 0.045, "output": 3.6 }, "model_page:Text tokens": { "Input": { "price": 0.25, "unit": "1M tokens" }, "Cached input": { "price": 0.025, "unit": "1M tokens" }, "Output": { "price": 2.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 5000000 }, "Tier 2": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "TPM": 180000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1754425928, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-5 Mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts. For most new low-latency, high-volume workloads, we recommend starting with [GPT-5.6 Terra](/api/docs/models/gpt-5.6-terra).", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5-mini", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5-mini-2025-08-07", "record_kind": "snapshot", "canonical_model": "gpt-5-mini", "display_name": "GPT-5 Mini (snapshot gpt-5-mini-2025-08-07)", "description": "Strong intelligence for cost sensitive, low latency, high volume workloads", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5-mini-2025-08-07", "family": "gpt-5", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-08-07", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2024-05-31", "context_window": 400000, "max_input": 272000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": false, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "mcp", "web_search" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 0.25, "_unit": "per 1M tokens", "cached_input": 0.025, "output": 2.0 }, "batch": { "input": 0.125, "_unit": "per 1M tokens", "cached_input": 0.0125, "output": 1.0 }, "flex": { "input": 0.125, "_unit": "per 1M tokens", "cached_input": 0.0125, "output": 1.0 }, "fast": { "input": 0.45, "_unit": "per 1M tokens", "cached_input": 0.045, "output": 3.6 }, "model_page:Text tokens": { "Input": { "price": 0.25, "unit": "1M tokens" }, "Cached input": { "price": 0.025, "unit": "1M tokens" }, "Output": { "price": 2.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 5000000 }, "Tier 2": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "TPM": 180000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1754425867, "openapi_enum": true }, "deprecation": [ { "announced": "2026-06-11", "shutdown_date": "2026-12-11", "replacement": "`gpt-5.6-terra`", "phase": "upcoming", "section": "2026-06-11: GPT-5 and o3 model deprecations", "source": "https://developers.openai.com/api/docs/deprecations#2026-06-11-gpt-5-and-o3-model-deprecations" }, { "announced": null, "shutdown_date": "2026-12-11", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-12-11", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5-mini", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-06-11-gpt-5-and-o3-model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5-nano", "record_kind": "model", "canonical_model": "gpt-5-nano", "display_name": "GPT-5 nano", "description": "Fastest, most cost-efficient version of GPT-5", "aliases": [], "snapshots": [ "gpt-5-nano-2025-08-07" ], "default_snapshot": "gpt-5-nano-2025-08-07", "family": "gpt-5", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-08-07", "release_date_source": "changelog", "knowledge_cutoff": "2024-05-31", "context_window": 400000, "max_input": 272000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs" ], "pricing": { "standard": { "input": 0.05, "_unit": "per 1M tokens", "cached_input": 0.005, "output": 0.4 }, "batch": { "input": 0.025, "_unit": "per 1M tokens", "cached_input": 0.0025, "output": 0.2 }, "flex": { "input": 0.025, "_unit": "per 1M tokens", "cached_input": 0.0025, "output": 0.2 }, "model_page:Text tokens": { "Input": { "price": 0.05, "unit": "1M tokens" }, "Cached input": { "price": 0.005, "unit": "1M tokens" }, "Output": { "price": 0.4, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "TPM": 180000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5-nano", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1754426384, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-5 Nano is our fastest, cheapest version of GPT-5. It's great for summarization and classification tasks. For most new speed- and cost-sensitive workloads, we recommend starting with [GPT-5.6 Luna](/api/docs/models/gpt-5.6-luna). Learn more in our [Model guidance](/api/docs/guides/latest-model) page.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5-nano", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5-nano-2025-08-07", "record_kind": "snapshot", "canonical_model": "gpt-5-nano", "display_name": "GPT-5 nano (snapshot gpt-5-nano-2025-08-07)", "description": "Fastest, most cost-efficient version of GPT-5", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5-nano-2025-08-07", "family": "gpt-5", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-08-07", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2024-05-31", "context_window": 400000, "max_input": 272000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs" ], "pricing": { "standard": { "input": 0.05, "_unit": "per 1M tokens", "cached_input": 0.005, "output": 0.4 }, "batch": { "input": 0.025, "_unit": "per 1M tokens", "cached_input": 0.0025, "output": 0.2 }, "flex": { "input": 0.025, "_unit": "per 1M tokens", "cached_input": 0.0025, "output": 0.2 }, "model_page:Text tokens": { "Input": { "price": 0.05, "unit": "1M tokens" }, "Cached input": { "price": 0.005, "unit": "1M tokens" }, "Output": { "price": 0.4, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "TPM": 180000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5-nano", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1754426303, "openapi_enum": true }, "deprecation": [ { "announced": "2026-06-11", "shutdown_date": "2026-12-11", "replacement": "`gpt-5.6-luna`", "phase": "upcoming", "section": "2026-06-11: GPT-5 and o3 model deprecations", "source": "https://developers.openai.com/api/docs/deprecations#2026-06-11-gpt-5-and-o3-model-deprecations" }, { "announced": null, "shutdown_date": "2026-12-11", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-12-11", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5-nano", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-06-11-gpt-5-and-o3-model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5-pro", "record_kind": "model", "canonical_model": "gpt-5-pro", "display_name": "GPT-5 Pro", "description": "Version of GPT-5 that produces smarter and more precise responses", "aliases": [], "snapshots": [ "gpt-5-pro-2025-10-06" ], "default_snapshot": "gpt-5-pro-2025-10-06", "family": "gpt-5", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-10-06", "release_date_source": "changelog", "knowledge_cutoff": "2024-09-30", "context_window": 400000, "max_input": null, "max_output": 272000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "high" ], "reasoning_effort_default": "high", "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": false, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 15.0, "_unit": "per 1M tokens", "output": 120.0 }, "batch": { "input": 7.5, "_unit": "per 1M tokens", "output": 60.0 }, "model_page:Text tokens": { "Input": { "price": 15.0, "unit": "1M tokens" }, "Output": { "price": 120.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5-pro", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1759469822, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-5 Pro uses more compute to think harder and provide consistently better answers. GPT-5 Pro is available in the [Responses API only](/api/docs/api-reference/responses) to enable support for multi-turn model interactions before responding to API requests, and other advanced API features in the future. Since GPT-5 Pro is designed to tackle tough problems, some requests may take several minutes to finish. To avoid timeouts, try using [background mode](/api/docs/guides/background). As our most advanced reasoning model, GPT-5 Pro defaults to (and only supports) `reasoning.effort: high`. GPT-5 Pr", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5-pro", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5-pro-2025-10-06", "record_kind": "snapshot", "canonical_model": "gpt-5-pro", "display_name": "GPT-5 Pro (snapshot gpt-5-pro-2025-10-06)", "description": "Version of GPT-5 that produces smarter and more precise responses", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5-pro-2025-10-06", "family": "gpt-5", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-10-06", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2024-09-30", "context_window": 400000, "max_input": null, "max_output": 272000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "high" ], "reasoning_effort_default": "high", "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": false, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 15.0, "_unit": "per 1M tokens", "output": 120.0 }, "batch": { "input": 7.5, "_unit": "per 1M tokens", "output": 60.0 }, "model_page:Text tokens": { "Input": { "price": 15.0, "unit": "1M tokens" }, "Output": { "price": 120.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5-pro", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1759469707, "openapi_enum": true }, "deprecation": [ { "announced": "2026-06-11", "shutdown_date": "2026-12-11", "replacement": "`gpt-5.6-sol` (`reasoning.mode: pro`)", "phase": "upcoming", "section": "2026-06-11: GPT-5 and o3 model deprecations", "source": "https://developers.openai.com/api/docs/deprecations#2026-06-11-gpt-5-and-o3-model-deprecations" }, { "announced": null, "shutdown_date": "2026-12-11", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-12-11", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5-pro", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-06-11-gpt-5-and-o3-model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5-search-api", "record_kind": "id_only", "canonical_model": "gpt-5-search-api", "display_name": "gpt-5-search-api", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "search", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "LIVE_DISCOVERED" ], "flags": [ "NO_MODEL_PAGE", "DOCUMENTATION_INCOMPLETE" ], "release_date": "2025-10-03", "release_date_source": "GET /v1/models created timestamp (approximation)", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "standard": { "input": 1.25, "_unit": "per 1M tokens", "cached_input": 0.125, "output": 10.0 } }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1759514629, "openapi_enum": false }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models/gpt-5-search-api -> 200", "get_model": { "status": 200, "id": "gpt-5-search-api", "object": "model", "created": 1759514629, "owned_by": "system", "shutdown_date": null } }, "sources": [ { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5-search-api-2025-10-14", "record_kind": "id_only", "canonical_model": "gpt-5-search-api-2025-10-14", "display_name": "gpt-5-search-api-2025-10-14", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "search", "status": [ "LIVE_VERIFIED", "LIVE_DISCOVERED" ], "flags": [ "DOCUMENTATION_INCOMPLETE" ], "release_date": "2025-10-09", "release_date_source": "GET /v1/models created timestamp (approximation)", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1760043960, "openapi_enum": false }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.1", "record_kind": "model", "canonical_model": "gpt-5.1", "display_name": "GPT-5.1", "description": "The best model for coding and agentic tasks with configurable reasoning effort", "aliases": [], "snapshots": [ "gpt-5.1-2025-11-13" ], "default_snapshot": "gpt-5.1-2025-11-13", "family": "gpt-5.1", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-11-13", "release_date_source": "changelog", "knowledge_cutoff": "2024-09-30", "context_window": 400000, "max_input": null, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "none", "low", "medium", "high" ], "reasoning_effort_default": "none", "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": true, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "apply_patch", "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 1.25, "_unit": "per 1M tokens", "cached_input": 0.125, "output": 10.0 }, "batch": { "input": 0.625, "_unit": "per 1M tokens", "cached_input": 0.0625, "output": 5.0 }, "flex": { "input": 0.625, "_unit": "per 1M tokens", "cached_input": 0.0625, "output": 5.0 }, "fast": { "input": 2.5, "_unit": "per 1M tokens", "cached_input": 0.25, "output": 20.0 }, "model_page:Text tokens": { "Input": { "price": 1.25, "unit": "1M tokens" }, "Cached input": { "price": 0.125, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.1", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1762800673, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-5.1 is our flagship model for coding and agentic tasks with configurable reasoning and non-reasoning effort. Learn more in our [GPT-5.1 model guidance](/api/docs/guides/latest-model?model=gpt-5.1). Reasoning.effort supports: none (default), low, medium, and high.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.1", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.1-2025-11-13", "record_kind": "snapshot", "canonical_model": "gpt-5.1", "display_name": "GPT-5.1 (snapshot gpt-5.1-2025-11-13)", "description": "The best model for coding and agentic tasks with configurable reasoning effort", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5.1-2025-11-13", "family": "gpt-5.1", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-11-13", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2024-09-30", "context_window": 400000, "max_input": null, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "none", "low", "medium", "high" ], "reasoning_effort_default": "none", "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": true, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "apply_patch", "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 1.25, "_unit": "per 1M tokens", "cached_input": 0.125, "output": 10.0 }, "batch": { "input": 0.625, "_unit": "per 1M tokens", "cached_input": 0.0625, "output": 5.0 }, "flex": { "input": 0.625, "_unit": "per 1M tokens", "cached_input": 0.0625, "output": 5.0 }, "fast": { "input": 2.5, "_unit": "per 1M tokens", "cached_input": 0.25, "output": 20.0 }, "model_page:Text tokens": { "Input": { "price": 1.25, "unit": "1M tokens" }, "Cached input": { "price": 0.125, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.1", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1762800353, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.1", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.1-chat-latest", "record_kind": "model", "canonical_model": "gpt-5.1-chat-latest", "display_name": "GPT-5.1 Chat", "description": "GPT-5.1 model used in ChatGPT", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5.1-chat-latest", "family": "chatgpt-latest", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "RETIRED" ], "flags": [ "STILL_LISTED_AFTER_DOCUMENTED_SHUTDOWN" ], "release_date": "2025-11-13", "release_date_source": "changelog", "knowledge_cutoff": "2024-09-30", "context_window": 128000, "max_input": 272000, "max_output": 16384, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "function_calling", "image_input", "streaming", "structured_outputs" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 1.25, "unit": "1M tokens" }, "Cached input": { "price": 0.125, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 50000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-chat-latest", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1762547951, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-07-23", "replacement": "`gpt-5.6-sol`", "phase": "past", "section": "2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown" }, { "announced": null, "shutdown_date": "2026-07-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-07-23", "intro": "GPT-5.1 Chat points to the GPT-5.1 snapshot currently used in ChatGPT. We recommend [GPT-6 Astra](/api/docs/models/gpt-6-astra) for most API usage, but feel free to use this GPT-5.1 Chat model to test our latest improvements for chat use cases.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.1-chat-latest", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.1-codex", "record_kind": "model", "canonical_model": "gpt-5.1-codex", "display_name": "GPT-5.1-Codex", "description": "A version of GPT-5.1 optimized for agentic coding in Codex.", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5.1-codex", "family": "codex", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "RETIRED" ], "flags": [ "STILL_LISTED_AFTER_DOCUMENTED_SHUTDOWN" ], "release_date": "2025-11-13", "release_date_source": "changelog", "knowledge_cutoff": "2024-09-30", "context_window": 400000, "max_input": null, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" } ], "tools": [ "function_calling", "web_search" ], "features_documented": [ "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 1.25, "unit": "1M tokens" }, "Cached input": { "price": 0.125, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1762988221, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-07-23", "replacement": "`gpt-5.6-sol`", "phase": "past", "section": "2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown" }, { "announced": null, "shutdown_date": "2026-07-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-07-23", "intro": "GPT-5.1-Codex is a version of GPT-5 optimized for agentic coding tasks in [Codex](https://developers.openai.com/codex) or similar environments. It's available in the [Responses API](/api/docs/api-reference/responses) only and the underlying model snapshot will be regularly updated. If you want to learn more about prompting GPT-5.1-Codex, refer to our [dedicated guide](/cookbook/examples/gpt-5/codex_prompting_guide)", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models/gpt-5.1-codex -> 200", "get_model": { "status": 200, "id": "gpt-5.1-codex", "object": "model", "created": 1762988221, "owned_by": "system", "shutdown_date": "2026-07-23" } }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.1-codex", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.1-codex-max", "record_kind": "model", "canonical_model": "gpt-5.1-codex-max", "display_name": "GPT-5.1-Codex-Max", "description": "A version of GPT-5.1-codex optimized for long running tasks.", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5.1-codex-max", "family": "codex", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "RETIRED" ], "flags": [ "STILL_LISTED_AFTER_DOCUMENTED_SHUTDOWN" ], "release_date": "2025-12-04", "release_date_source": "changelog", "knowledge_cutoff": "2024-09-30", "context_window": 400000, "max_input": null, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" } ], "tools": [ "function_calling", "web_search" ], "features_documented": [ "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 1.25, "unit": "1M tokens" }, "Cached input": { "price": 0.125, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-max", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1763671532, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-07-23", "replacement": "`gpt-5.6-sol`", "phase": "past", "section": "2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown" }, { "announced": null, "shutdown_date": "2026-07-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-07-23", "intro": "GPT‑5.1-Codex-Max is purpose-built for agentic coding. It's only available in the [Responses API](/api/docs/api-reference/responses). Learn how to get the most of GPT-5.1-Codex-Max in the [prompting guide](/cookbook/examples/gpt-5/codex_prompting_guide).", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-max", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.1-codex-mini", "record_kind": "model", "canonical_model": "gpt-5.1-codex-mini", "display_name": "GPT-5.1-Codex Mini", "description": "Smaller, more cost-effective, less-capable version of GPT-5.1-Codex", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5.1-codex-mini", "family": "codex", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "RETIRED" ], "flags": [ "STILL_LISTED_AFTER_DOCUMENTED_SHUTDOWN" ], "release_date": "2025-11-13", "release_date_source": "changelog", "knowledge_cutoff": "2024-09-30", "context_window": 400000, "max_input": null, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": true, "stored_completions": true, "distillation": true, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" } ], "tools": [ "function_calling", "web_search" ], "features_documented": [ "evals", "function_calling", "image_input", "prompt_caching", "stored_completions", "streaming", "structured_outputs" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 0.25, "unit": "1M tokens" }, "Cached input": { "price": 0.025, "unit": "1M tokens" }, "Output": { "price": 2.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 5000000 }, "Tier 2": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "TPM": 180000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1763007109, "openapi_enum": false }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-07-23", "replacement": "`gpt-5.6-terra`", "phase": "past", "section": "2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown" }, { "announced": null, "shutdown_date": "2026-07-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-07-23", "intro": "GPT-5.1-Codex Mini is a smaller, more cost-effective, less-capable version of GPT-5.1-Codex.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-mini", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.2", "record_kind": "model", "canonical_model": "gpt-5.2", "display_name": "GPT-5.2", "description": "Previous flagship model for professional work with configurable reasoning effort", "aliases": [], "snapshots": [ "gpt-5.2-2025-12-11" ], "default_snapshot": "gpt-5.2-2025-12-11", "family": "gpt-5.2", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-12-11", "release_date_source": "changelog", "knowledge_cutoff": "2025-08-31", "context_window": 400000, "max_input": null, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "none", "low", "medium", "high", "xhigh" ], "reasoning_effort_default": "none", "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": true, "tool_apply_patch": true, "tool_skills": true, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "apply_patch", "code_interpreter", "file_search", "function_calling", "hosted_shell", "image_generation", "mcp", "skills", "web_search" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 1.75, "_unit": "per 1M tokens", "cached_input": 0.175, "output": 14.0 }, "batch": { "input": 0.875, "_unit": "per 1M tokens", "cached_input": 0.0875, "output": 7.0 }, "flex": { "input": 0.875, "_unit": "per 1M tokens", "cached_input": 0.0875, "output": 7.0 }, "fast": { "input": 3.5, "_unit": "per 1M tokens", "cached_input": 0.35, "output": 28.0 }, "model_page:Text tokens": { "Input": { "price": 1.75, "unit": "1M tokens" }, "Cached input": { "price": 0.175, "unit": "1M tokens" }, "Output": { "price": 14.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.2", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1765313051, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-5.2 is our previous flagship model for complex professional work. We recommend using the latest [GPT-6 Astra](/api/docs/models/gpt-6-astra). Learn more on the [Model guidance](/api/docs/guides/latest-model) page. Reasoning.effort supports: none (default), low, medium, high and xhigh.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.2", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.2-2025-12-11", "record_kind": "snapshot", "canonical_model": "gpt-5.2", "display_name": "GPT-5.2 (snapshot gpt-5.2-2025-12-11)", "description": "Previous flagship model for professional work with configurable reasoning effort", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5.2-2025-12-11", "family": "gpt-5.2", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-12-11", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2025-08-31", "context_window": 400000, "max_input": null, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "none", "low", "medium", "high", "xhigh" ], "reasoning_effort_default": "none", "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": true, "tool_apply_patch": true, "tool_skills": true, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "apply_patch", "code_interpreter", "file_search", "function_calling", "hosted_shell", "image_generation", "mcp", "skills", "web_search" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 1.75, "_unit": "per 1M tokens", "cached_input": 0.175, "output": 14.0 }, "batch": { "input": 0.875, "_unit": "per 1M tokens", "cached_input": 0.0875, "output": 7.0 }, "flex": { "input": 0.875, "_unit": "per 1M tokens", "cached_input": 0.0875, "output": 7.0 }, "fast": { "input": 3.5, "_unit": "per 1M tokens", "cached_input": 0.35, "output": 28.0 }, "model_page:Text tokens": { "Input": { "price": 1.75, "unit": "1M tokens" }, "Cached input": { "price": 0.175, "unit": "1M tokens" }, "Output": { "price": 14.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.2", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1765313028, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.2", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.2-chat-latest", "record_kind": "model", "canonical_model": "gpt-5.2-chat-latest", "display_name": "GPT-5.2 Chat", "description": "GPT-5.2 model used in ChatGPT", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5.2-chat-latest", "family": "chatgpt-latest", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "RETIRED" ], "flags": [ "STILL_LISTED_AFTER_DOCUMENTED_SHUTDOWN" ], "release_date": "2025-12-11", "release_date_source": "changelog", "knowledge_cutoff": "2025-08-31", "context_window": 128000, "max_input": 272000, "max_output": 16384, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "function_calling", "image_input", "streaming", "structured_outputs" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 1.75, "unit": "1M tokens" }, "Cached input": { "price": 0.175, "unit": "1M tokens" }, "Output": { "price": 14.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 50000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.2-chat-latest", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1765344352, "openapi_enum": true }, "deprecation": [ { "announced": "2026-05-08", "shutdown_date": "2026-08-10", "replacement": "`gpt-5.6-sol`", "phase": "past", "section": "2026-05-08: `gpt-5.2-chat-latest` and `gpt-5.3-chat-latest` model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-05-08-gpt-5-2-chat-latest-and-gpt-5-3-chat-latest-model-snapshots" }, { "announced": null, "shutdown_date": "2026-08-10", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-08-10", "intro": "GPT-5.2 Chat points to the GPT-5.2 snapshot used in ChatGPT. This model has been deprecated. We recommend [GPT-6 Astra](/api/docs/models/gpt-6-astra) for most API usage.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.2-chat-latest", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-05-08-gpt-5-2-chat-latest-and-gpt-5-3-chat-latest-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.2-codex", "record_kind": "model", "canonical_model": "gpt-5.2-codex", "display_name": "GPT-5.2-Codex", "description": "Our most intelligent coding model optimized for long-horizon, agentic coding tasks.", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5.2-codex", "family": "codex", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "RETIRED" ], "flags": [ "STILL_LISTED_AFTER_DOCUMENTED_SHUTDOWN" ], "release_date": "2026-01-14", "release_date_source": "changelog", "knowledge_cutoff": "2025-08-31", "context_window": 400000, "max_input": 272000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "low", "medium", "high", "xhigh" ], "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": true, "tool_apply_patch": false, "tool_skills": true, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" } ], "tools": [ "function_calling", "hosted_shell", "skills", "web_search" ], "features_documented": [ "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 1.75, "unit": "1M tokens" }, "Cached input": { "price": 0.175, "unit": "1M tokens" }, "Output": { "price": 14.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.2-codex", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1766164985, "openapi_enum": false }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-07-23", "replacement": "`gpt-5.6-sol`", "phase": "past", "section": "2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown" }, { "announced": null, "shutdown_date": "2026-07-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-07-23", "intro": "GPT-5.2-Codex is an upgraded version of GPT-5.2 optimized for agentic coding tasks in [Codex](https://developers.openai.com/codex) or similar environments. GPT-5.2-Codex supports `low`, `medium`, `high`, and `xhigh` reasoning effort settings. If you want to learn more about prompting GPT-5.2-Codex, refer to our [dedicated guide](/cookbook/examples/gpt-5/codex_prompting_guide).", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.2-codex", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.2-pro", "record_kind": "model", "canonical_model": "gpt-5.2-pro", "display_name": "GPT-5.2 Pro", "description": "Previous pro model for professional work that produces smarter and more precise responses.", "aliases": [], "snapshots": [ "gpt-5.2-pro-2025-12-11" ], "default_snapshot": "gpt-5.2-pro-2025-12-11", "family": "gpt-5.2", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-12-11", "release_date_source": "changelog", "knowledge_cutoff": "2025-08-31", "context_window": 400000, "max_input": null, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": false, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" } ], "tools": [ "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "file_search", "function_calling", "image_generation", "image_input", "mcp", "streaming", "web_search" ], "pricing": { "standard": { "input": 21.0, "_unit": "per 1M tokens", "output": 168.0 }, "batch": { "input": 10.5, "_unit": "per 1M tokens", "output": 84.0 }, "model_page:Text tokens": { "Input": { "price": 21.0, "unit": "1M tokens" }, "Output": { "price": 168.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "Standard": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } }, "Long Context": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": "128k input tokens", "tiers": { "Tier 1": { "RPM": 100, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 250, "TPM": 500000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 500, "TPM": 1000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 1000, "TPM": 5000000, "Batch queue limit": 100000000 }, "Tier 5": { "RPM": 4000, "TPM": 10000000, "Batch queue limit": 1000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.2-pro", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1765343983, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-5.2 Pro is our previous pro model for complex professional work. We recommend using [GPT-5.5 Pro](/api/docs/models/gpt-5.5-pro) for the latest pro model. GPT-5.2 Pro is available in the Responses API only to enable support for multi-turn model interactions before responding to API requests, and other advanced API features in the future. Since GPT-5.2 Pro is designed to tackle tough problems, some requests may take several minutes to finish. To avoid timeouts, try using background mode. GPT-5.2 Pro supports reasoning.effort: medium, high, xhigh.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.2-pro", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.2-pro-2025-12-11", "record_kind": "snapshot", "canonical_model": "gpt-5.2-pro", "display_name": "GPT-5.2 Pro (snapshot gpt-5.2-pro-2025-12-11)", "description": "Previous pro model for professional work that produces smarter and more precise responses.", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5.2-pro-2025-12-11", "family": "gpt-5.2", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-12-11", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2025-08-31", "context_window": 400000, "max_input": null, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": false, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" } ], "tools": [ "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "file_search", "function_calling", "image_generation", "image_input", "mcp", "streaming", "web_search" ], "pricing": { "standard": { "input": 21.0, "_unit": "per 1M tokens", "output": 168.0 }, "batch": { "input": 10.5, "_unit": "per 1M tokens", "output": 84.0 }, "model_page:Text tokens": { "Input": { "price": 21.0, "unit": "1M tokens" }, "Output": { "price": 168.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "Standard": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } }, "Long Context": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": "128k input tokens", "tiers": { "Tier 1": { "RPM": 100, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 250, "TPM": 500000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 500, "TPM": 1000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 1000, "TPM": 5000000, "Batch queue limit": 100000000 }, "Tier 5": { "RPM": 4000, "TPM": 10000000, "Batch queue limit": 1000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.2-pro", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1765343959, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.2-pro", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.3-chat-latest", "record_kind": "model", "canonical_model": "gpt-5.3-chat-latest", "display_name": "GPT-5.3 Chat", "description": "GPT-5.3 Instant model used in ChatGPT", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5.3-chat-latest", "family": "chatgpt-latest", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "RETIRED" ], "flags": [ "STILL_LISTED_AFTER_DOCUMENTED_SHUTDOWN" ], "release_date": "2026-03-03", "release_date_source": "changelog", "knowledge_cutoff": "2025-08-31", "context_window": 128000, "max_input": 272000, "max_output": 16384, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "function_calling", "image_input", "streaming", "structured_outputs" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 1.75, "unit": "1M tokens" }, "Cached input": { "price": 0.175, "unit": "1M tokens" }, "Output": { "price": 14.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 50000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.3-chat-latest", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1772236571, "openapi_enum": true }, "deprecation": [ { "announced": "2026-05-08", "shutdown_date": "2026-08-10", "replacement": "`gpt-5.6-sol`", "phase": "past", "section": "2026-05-08: `gpt-5.2-chat-latest` and `gpt-5.3-chat-latest` model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-05-08-gpt-5-2-chat-latest-and-gpt-5-3-chat-latest-model-snapshots" }, { "announced": null, "shutdown_date": "2026-08-10", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-08-10", "intro": "GPT-5.3 Chat points to the GPT-5.3 Instant snapshot used in ChatGPT. This model has been deprecated. We recommend [GPT-6 Astra](/api/docs/models/gpt-6-astra) for most API usage.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.3-chat-latest", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-05-08-gpt-5-2-chat-latest-and-gpt-5-3-chat-latest-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.3-codex", "record_kind": "model", "canonical_model": "gpt-5.3-codex", "display_name": "GPT-5.3-Codex", "description": "The most capable agentic coding model to date.", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5.3-codex", "family": "codex", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-02-24", "release_date_source": "changelog", "knowledge_cutoff": "2025-08-31", "context_window": 400000, "max_input": 272000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "low", "medium", "high", "xhigh" ], "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": true, "tool_apply_patch": false, "tool_skills": true, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" } ], "tools": [ "function_calling", "hosted_shell", "skills", "web_search" ], "features_documented": [ "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 1.75, "_unit": "per 1M tokens", "cached_input": 0.175, "output": 14.0 }, "fast": { "input": 3.5, "_unit": "per 1M tokens", "cached_input": 0.35, "output": 28.0 }, "model_page:Text tokens": { "Input": { "price": 1.75, "unit": "1M tokens" }, "Cached input": { "price": 0.175, "unit": "1M tokens" }, "Output": { "price": 14.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.3-codex", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1770537915, "openapi_enum": false }, "deprecation": [], "shutdown_date": null, "intro": "GPT-5.3-Codex is optimized for agentic coding tasks in [Codex](https://developers.openai.com/codex) or similar environments. GPT-5.3-Codex supports `low`, `medium`, `high`, and `xhigh` reasoning effort settings. If you want to learn more about prompting GPT-5.3-Codex, refer to our [dedicated guide](/cookbook/examples/gpt-5/codex_prompting_guide).", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.3-codex", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.4", "record_kind": "model", "canonical_model": "gpt-5.4", "display_name": "GPT-5.4", "description": "A more affordable model for coding and professional work.", "aliases": [], "snapshots": [ "gpt-5.4-2026-03-05" ], "default_snapshot": "gpt-5.4-2026-03-05", "family": "gpt-5.4", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-03-05", "release_date_source": "changelog", "knowledge_cutoff": "2025-08-31", "context_window": 1050000, "max_input": null, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "none", "low", "medium", "high", "xhigh" ], "reasoning_effort_default": "none", "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": true, "long_context_tier_272k": true, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": true, "tool_hosted_shell": true, "tool_apply_patch": true, "tool_skills": true, "tool_tool_search": true, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "apply_patch", "code_interpreter", "computer_use", "file_search", "function_calling", "hosted_shell", "image_generation", "mcp", "skills", "tool_search", "web_search" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 2.5, "_unit": "per 1M tokens", "cached_input": 0.25, "output": 15.0 }, "standard_long_context": { "input": 5.0, "_unit": "per 1M tokens", "cached_input": 0.5, "output": 22.5 }, "batch": { "input": 1.25, "_unit": "per 1M tokens", "cached_input": 0.13, "output": 7.5 }, "batch_long_context": { "input": 2.5, "_unit": "per 1M tokens", "cached_input": 0.25, "output": 11.25 }, "flex": { "input": 1.25, "_unit": "per 1M tokens", "cached_input": 0.13, "output": 7.5 }, "flex_long_context": { "input": 2.5, "_unit": "per 1M tokens", "cached_input": 0.25, "output": 11.25 }, "fast": { "input": 5.0, "_unit": "per 1M tokens", "cached_input": 0.5, "output": 30.0 }, "model_page:Text tokens": { "Input": { "price": 2.5, "unit": "1M tokens" }, "Cached input": { "price": 0.25, "unit": "1M tokens" }, "Output": { "price": 15.0, "unit": "1M tokens" } }, "notes": [ "For models with a 1.05M context window (GPT-5.4 and GPT-5.4 Pro), prompts with >272K input tokens are priced at 2x input and 1.5x output for the full session for standard, batch, and flex.", "Regional processing (data residency) endpoints are charged a 10% uplift for GPT-5.4 and GPT-5.4 Pro." ] }, "rate_limits": { "documented_tiers": { "Standard": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } }, "Long Context": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": "272K input tokens", "tiers": { "Tier 1": { "RPM": 200, "TPM": 400000, "Batch queue limit": 5000000 }, "Tier 2": { "RPM": 500, "TPM": 1000000, "Batch queue limit": 40000000 }, "Tier 3": { "RPM": 1000, "TPM": 2000000, "Batch queue limit": 80000000 }, "Tier 4": { "RPM": 2000, "TPM": 10000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 8000, "TPM": 20000000, "Batch queue limit": 2000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.4", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1772691852, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-5.4 is a flagship model for complex professional work. Learn more in our [GPT-5.4 model guidance](/api/docs/guides/latest-model?model=gpt-5.4). Reasoning.effort supports: none (default), low, medium, high and xhigh.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.4", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.4-2026-03-05", "record_kind": "snapshot", "canonical_model": "gpt-5.4", "display_name": "GPT-5.4 (snapshot gpt-5.4-2026-03-05)", "description": "A more affordable model for coding and professional work.", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5.4-2026-03-05", "family": "gpt-5.4", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-03-05", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2025-08-31", "context_window": 1050000, "max_input": null, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "none", "low", "medium", "high", "xhigh" ], "reasoning_effort_default": "none", "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": true, "long_context_tier_272k": true, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": true, "tool_hosted_shell": true, "tool_apply_patch": true, "tool_skills": true, "tool_tool_search": true, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "apply_patch", "code_interpreter", "computer_use", "file_search", "function_calling", "hosted_shell", "image_generation", "mcp", "skills", "tool_search", "web_search" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 2.5, "_unit": "per 1M tokens", "cached_input": 0.25, "output": 15.0 }, "standard_long_context": { "input": 5.0, "_unit": "per 1M tokens", "cached_input": 0.5, "output": 22.5 }, "batch": { "input": 1.25, "_unit": "per 1M tokens", "cached_input": 0.13, "output": 7.5 }, "batch_long_context": { "input": 2.5, "_unit": "per 1M tokens", "cached_input": 0.25, "output": 11.25 }, "flex": { "input": 1.25, "_unit": "per 1M tokens", "cached_input": 0.13, "output": 7.5 }, "flex_long_context": { "input": 2.5, "_unit": "per 1M tokens", "cached_input": 0.25, "output": 11.25 }, "fast": { "input": 5.0, "_unit": "per 1M tokens", "cached_input": 0.5, "output": 30.0 }, "model_page:Text tokens": { "Input": { "price": 2.5, "unit": "1M tokens" }, "Cached input": { "price": 0.25, "unit": "1M tokens" }, "Output": { "price": 15.0, "unit": "1M tokens" } }, "notes": [ "For models with a 1.05M context window (GPT-5.4 and GPT-5.4 Pro), prompts with >272K input tokens are priced at 2x input and 1.5x output for the full session for standard, batch, and flex.", "Regional processing (data residency) endpoints are charged a 10% uplift for GPT-5.4 and GPT-5.4 Pro." ] }, "rate_limits": { "documented_tiers": { "Standard": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } }, "Long Context": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": "272K input tokens", "tiers": { "Tier 1": { "RPM": 200, "TPM": 400000, "Batch queue limit": 5000000 }, "Tier 2": { "RPM": 500, "TPM": 1000000, "Batch queue limit": 40000000 }, "Tier 3": { "RPM": 1000, "TPM": 2000000, "Batch queue limit": 80000000 }, "Tier 4": { "RPM": 2000, "TPM": 10000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 8000, "TPM": 20000000, "Batch queue limit": 2000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.4", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1772654062, "openapi_enum": false }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.4", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.4-cyber", "record_kind": "id_only", "canonical_model": "gpt-5.4-cyber", "display_name": "gpt-5.4-cyber", "description": "Cybersecurity model, deprecated 2026-09-11, shutdown 2026-10-01 (replacement gpt-5.6-cyber).", "aliases": [], "snapshots": [], "default_snapshot": null, "family": "cyber-daybreak", "status": [ "DEPRECATED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": "Daybreak program (deprecations page only; shutdown 2026-10-01)", "availability": { "account": "Daybreak program (deprecations page only; shutdown 2026-10-01)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2026-09-11", "shutdown_date": "2026-10-01", "replacement": "`gpt-5.6-cyber`", "phase": "upcoming", "section": "2026-09-11: GPT-5.4-Cyber", "source": "https://developers.openai.com/api/docs/deprecations#2026-09-11-gpt-5-4-cyber" } ], "shutdown_date": "2026-10-01", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2026-09-11-gpt-5-4-cyber", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.4-mini", "record_kind": "model", "canonical_model": "gpt-5.4-mini", "display_name": "GPT-5.4 Mini", "description": "Our strongest mini model yet for coding, computer use, and subagents", "aliases": [], "snapshots": [ "gpt-5.4-mini-2026-03-17" ], "default_snapshot": "gpt-5.4-mini-2026-03-17", "family": "gpt-5.4", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-03-17", "release_date_source": "changelog", "knowledge_cutoff": "2025-08-31", "context_window": 400000, "max_input": 272000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "none", "low", "medium", "high", "xhigh" ], "reasoning_effort_default": "none", "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": true, "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": true, "tool_hosted_shell": true, "tool_apply_patch": true, "tool_skills": true, "tool_tool_search": true, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "apply_patch", "code_interpreter", "computer_use", "file_search", "function_calling", "hosted_shell", "image_generation", "mcp", "skills", "tool_search", "web_search" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 0.75, "_unit": "per 1M tokens", "cached_input": 0.075, "output": 4.5 }, "batch": { "input": 0.375, "_unit": "per 1M tokens", "cached_input": 0.0375, "output": 2.25 }, "flex": { "input": 0.375, "_unit": "per 1M tokens", "cached_input": 0.0375, "output": 2.25 }, "fast": { "input": 1.5, "_unit": "per 1M tokens", "cached_input": 0.15, "output": 9.0 }, "model_page:Text tokens": { "Input": { "price": 0.75, "unit": "1M tokens" }, "Cached input": { "price": 0.075, "unit": "1M tokens" }, "Output": { "price": 4.5, "unit": "1M tokens" } }, "notes": [ "Regional processing (data residency) endpoints are charged a 10% uplift for GPT-5.4 Mini." ] }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 5000000 }, "Tier 2": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "TPM": 180000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.4-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1773451123, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-5.4 Mini brings the strengths of GPT-5.4 to a faster, more efficient model designed for high-volume workloads. Learn more in our [Model guidance](/api/docs/guides/latest-model) page. Reasoning.effort supports: none (default), low, medium, high and xhigh.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "POST /v1/responses ('Reply with OK.', max_output_tokens 16) -> 200, model echoed: gpt-5.4-mini-2026-03-17", "post_responses": { "status": 200, "request": { "model": "gpt-5.4-mini", "input": "Reply with OK.", "max_output_tokens": 16, "reasoning": { "effort": "none" } }, "model_echo": "gpt-5.4-mini-2026-03-17", "status_field": "completed", "incomplete_reason": null, "service_tier": "default", "usage": { "input_tokens": 10, "input_tokens_details": { "cache_write_tokens": 0, "cached_tokens": 0 }, "output_tokens": 5, "output_tokens_details": { "reasoning_tokens": 0 }, "total_tokens": 15 }, "reasoning_tokens": 0, "output_text": "OK", "est_cost_usd": 3e-05 } }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.4-mini", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.4-mini-2026-03-17", "record_kind": "snapshot", "canonical_model": "gpt-5.4-mini", "display_name": "GPT-5.4 Mini (snapshot gpt-5.4-mini-2026-03-17)", "description": "Our strongest mini model yet for coding, computer use, and subagents", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5.4-mini-2026-03-17", "family": "gpt-5.4", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-03-17", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2025-08-31", "context_window": 400000, "max_input": 272000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "none", "low", "medium", "high", "xhigh" ], "reasoning_effort_default": "none", "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": true, "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": true, "tool_hosted_shell": true, "tool_apply_patch": true, "tool_skills": true, "tool_tool_search": true, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "apply_patch", "code_interpreter", "computer_use", "file_search", "function_calling", "hosted_shell", "image_generation", "mcp", "skills", "tool_search", "web_search" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 0.75, "_unit": "per 1M tokens", "cached_input": 0.075, "output": 4.5 }, "batch": { "input": 0.375, "_unit": "per 1M tokens", "cached_input": 0.0375, "output": 2.25 }, "flex": { "input": 0.375, "_unit": "per 1M tokens", "cached_input": 0.0375, "output": 2.25 }, "fast": { "input": 1.5, "_unit": "per 1M tokens", "cached_input": 0.15, "output": 9.0 }, "model_page:Text tokens": { "Input": { "price": 0.75, "unit": "1M tokens" }, "Cached input": { "price": 0.075, "unit": "1M tokens" }, "Output": { "price": 4.5, "unit": "1M tokens" } }, "notes": [ "Regional processing (data residency) endpoints are charged a 10% uplift for GPT-5.4 Mini." ] }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 5000000 }, "Tier 2": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "TPM": 180000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.4-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1773451076, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.4-mini", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.4-nano", "record_kind": "model", "canonical_model": "gpt-5.4-nano", "display_name": "GPT-5.4 nano", "description": "Our cheapest GPT-5.4-class model for simple high-volume tasks", "aliases": [], "snapshots": [ "gpt-5.4-nano-2026-03-17" ], "default_snapshot": "gpt-5.4-nano-2026-03-17", "family": "gpt-5.4", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-03-17", "release_date_source": "changelog", "knowledge_cutoff": "2025-08-31", "context_window": 400000, "max_input": 272000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "none", "low", "medium", "high", "xhigh" ], "reasoning_effort_default": "none", "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": true, "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": true, "tool_apply_patch": true, "tool_skills": true, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "apply_patch", "code_interpreter", "file_search", "function_calling", "hosted_shell", "image_generation", "mcp", "skills", "web_search" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 0.2, "_unit": "per 1M tokens", "cached_input": 0.02, "output": 1.25 }, "batch": { "input": 0.1, "_unit": "per 1M tokens", "cached_input": 0.01, "output": 0.625 }, "flex": { "input": 0.1, "_unit": "per 1M tokens", "cached_input": 0.01, "output": 0.625 }, "model_page:Text tokens": { "Input": { "price": 0.2, "unit": "1M tokens" }, "Cached input": { "price": 0.02, "unit": "1M tokens" }, "Output": { "price": 1.25, "unit": "1M tokens" } }, "notes": [ "Regional processing (data residency) endpoints are charged a 10% uplift for GPT-5.4 nano." ] }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "TPM": 180000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.4-nano", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1773450870, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-5.4 nano is designed for tasks where speed and cost matter most like classification, data extraction, ranking, and sub-agents. Learn more in our [Model guidance](/api/docs/guides/latest-model) page. Reasoning.effort supports: none (default), low, medium, high and xhigh.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.4-nano", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.4-nano-2026-03-17", "record_kind": "snapshot", "canonical_model": "gpt-5.4-nano", "display_name": "GPT-5.4 nano (snapshot gpt-5.4-nano-2026-03-17)", "description": "Our cheapest GPT-5.4-class model for simple high-volume tasks", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5.4-nano-2026-03-17", "family": "gpt-5.4", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-03-17", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2025-08-31", "context_window": 400000, "max_input": 272000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "none", "low", "medium", "high", "xhigh" ], "reasoning_effort_default": "none", "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": true, "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": true, "tool_apply_patch": true, "tool_skills": true, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "apply_patch", "code_interpreter", "file_search", "function_calling", "hosted_shell", "image_generation", "mcp", "skills", "web_search" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 0.2, "_unit": "per 1M tokens", "cached_input": 0.02, "output": 1.25 }, "batch": { "input": 0.1, "_unit": "per 1M tokens", "cached_input": 0.01, "output": 0.625 }, "flex": { "input": 0.1, "_unit": "per 1M tokens", "cached_input": 0.01, "output": 0.625 }, "model_page:Text tokens": { "Input": { "price": 0.2, "unit": "1M tokens" }, "Cached input": { "price": 0.02, "unit": "1M tokens" }, "Output": { "price": 1.25, "unit": "1M tokens" } }, "notes": [ "Regional processing (data residency) endpoints are charged a 10% uplift for GPT-5.4 nano." ] }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "TPM": 180000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.4-nano", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1773450837, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.4-nano", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.4-pro", "record_kind": "model", "canonical_model": "gpt-5.4-pro", "display_name": "GPT-5.4 Pro", "description": "Version of GPT-5.4 that produces smarter and more precise responses.", "aliases": [], "snapshots": [ "gpt-5.4-pro-2026-03-05" ], "default_snapshot": "gpt-5.4-pro-2026-03-05", "family": "gpt-5.4", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-03-05", "release_date_source": "changelog", "knowledge_cutoff": "2025-08-31", "context_window": 1050000, "max_input": null, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "medium", "high", "xhigh" ], "reasoning_effort_default": "medium", "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": true, "long_context_tier_272k": true, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": false, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": true, "tool_hosted_shell": false, "tool_apply_patch": true, "tool_skills": false, "tool_tool_search": true, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" } ], "tools": [ "apply_patch", "computer_use", "file_search", "function_calling", "image_generation", "mcp", "tool_search", "web_search" ], "features_documented": [ "file_search", "function_calling", "image_generation", "image_input", "mcp", "streaming", "web_search" ], "pricing": { "standard": { "input": 30.0, "_unit": "per 1M tokens", "output": 180.0 }, "standard_long_context": { "input": 60.0, "_unit": "per 1M tokens", "output": 270.0 }, "batch": { "input": 15.0, "_unit": "per 1M tokens", "output": 90.0 }, "batch_long_context": { "input": 30.0, "_unit": "per 1M tokens", "output": 135.0 }, "flex": { "input": 15.0, "_unit": "per 1M tokens", "output": 90.0 }, "flex_long_context": { "input": 30.0, "_unit": "per 1M tokens", "output": 135.0 }, "model_page:Text tokens": { "Input": { "price": 30.0, "unit": "1M tokens" }, "Output": { "price": 180.0, "unit": "1M tokens" } }, "notes": [ "For models with a 1.05M context window (GPT-5.4 and GPT-5.4 Pro), prompts with >272K input tokens are priced at 2x input and 1.5x output for the full session for standard, batch, and flex.", "Regional processing (data residency) endpoints are charged a 10% uplift for GPT-5.4 and GPT-5.4 Pro." ] }, "rate_limits": { "documented_tiers": { "Standard": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 50, "TPM": 50000, "Batch queue limit": 900000 }, "Tier 2": { "RPM": 500, "TPM": 100000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 500, "TPM": 200000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 1000, "TPM": 400000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 1500, "TPM": 4000000, "Batch queue limit": 15000000000 } } }, "Long Context": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": "272K input tokens", "tiers": { "Tier 1": { "RPM": 20, "TPM": 40000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 50, "TPM": 100000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 100, "TPM": 200000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 200, "TPM": 1000000, "Batch queue limit": 100000000 }, "Tier 5": { "RPM": 800, "TPM": 2000000, "Batch queue limit": 1000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.4-pro", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1772659601, "openapi_enum": false }, "deprecation": [], "shutdown_date": null, "intro": "GPT-5.4 Pro uses more compute to think harder and provide consistently better answers. GPT-5.4 Pro is available in the Responses API only to enable support for multi-turn model interactions before responding to API requests, and other advanced API features in the future. Since GPT-5.4 Pro is designed to tackle tough problems, some requests may take several minutes to finish. To avoid timeouts, try using [background mode](/api/docs/guides/background). Reasoning.effort supports: medium (default), high and xhigh.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.4-pro", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.4-pro-2026-03-05", "record_kind": "snapshot", "canonical_model": "gpt-5.4-pro", "display_name": "GPT-5.4 Pro (snapshot gpt-5.4-pro-2026-03-05)", "description": "Version of GPT-5.4 that produces smarter and more precise responses.", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5.4-pro-2026-03-05", "family": "gpt-5.4", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-03-05", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2025-08-31", "context_window": 1050000, "max_input": null, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "medium", "high", "xhigh" ], "reasoning_effort_default": "medium", "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": true, "long_context_tier_272k": true, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": false, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": true, "tool_hosted_shell": false, "tool_apply_patch": true, "tool_skills": false, "tool_tool_search": true, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" } ], "tools": [ "apply_patch", "computer_use", "file_search", "function_calling", "image_generation", "mcp", "tool_search", "web_search" ], "features_documented": [ "file_search", "function_calling", "image_generation", "image_input", "mcp", "streaming", "web_search" ], "pricing": { "standard": { "input": 30.0, "_unit": "per 1M tokens", "output": 180.0 }, "standard_long_context": { "input": 60.0, "_unit": "per 1M tokens", "output": 270.0 }, "batch": { "input": 15.0, "_unit": "per 1M tokens", "output": 90.0 }, "batch_long_context": { "input": 30.0, "_unit": "per 1M tokens", "output": 135.0 }, "flex": { "input": 15.0, "_unit": "per 1M tokens", "output": 90.0 }, "flex_long_context": { "input": 30.0, "_unit": "per 1M tokens", "output": 135.0 }, "model_page:Text tokens": { "Input": { "price": 30.0, "unit": "1M tokens" }, "Output": { "price": 180.0, "unit": "1M tokens" } }, "notes": [ "For models with a 1.05M context window (GPT-5.4 and GPT-5.4 Pro), prompts with >272K input tokens are priced at 2x input and 1.5x output for the full session for standard, batch, and flex.", "Regional processing (data residency) endpoints are charged a 10% uplift for GPT-5.4 and GPT-5.4 Pro." ] }, "rate_limits": { "documented_tiers": { "Standard": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 50, "TPM": 50000, "Batch queue limit": 900000 }, "Tier 2": { "RPM": 500, "TPM": 100000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 500, "TPM": 200000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 1000, "TPM": 400000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 1500, "TPM": 4000000, "Batch queue limit": 15000000000 } } }, "Long Context": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": "272K input tokens", "tiers": { "Tier 1": { "RPM": 20, "TPM": 40000, "Batch queue limit": 2000000 }, "Tier 2": { "RPM": 50, "TPM": 100000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 100, "TPM": 200000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 200, "TPM": 1000000, "Batch queue limit": 100000000 }, "Tier 5": { "RPM": 800, "TPM": 2000000, "Batch queue limit": 1000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.4-pro", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1772659657, "openapi_enum": false }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.4-pro", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.5", "record_kind": "model", "canonical_model": "gpt-5.5", "display_name": "GPT-5.5", "description": "A new class of intelligence for coding and professional work.", "aliases": [], "snapshots": [ "gpt-5.5-2026-04-23" ], "default_snapshot": "gpt-5.5-2026-04-23", "family": "gpt-5.5", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-04-24", "release_date_source": "changelog", "knowledge_cutoff": "2025-12-01", "context_window": 1050000, "max_input": null, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "none", "low", "medium", "high", "xhigh" ], "reasoning_effort_default": "medium", "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": true, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": true, "tool_hosted_shell": true, "tool_apply_patch": true, "tool_skills": true, "tool_tool_search": true, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "apply_patch", "code_interpreter", "computer_use", "file_search", "function_calling", "hosted_shell", "image_generation", "mcp", "skills", "tool_search", "web_search" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 5.0, "_unit": "per 1M tokens", "cached_input": 0.5, "output": 30.0 }, "standard_long_context": { "input": 10.0, "_unit": "per 1M tokens", "cached_input": 1.0, "output": 45.0 }, "batch": { "input": 2.5, "_unit": "per 1M tokens", "cached_input": 0.25, "output": 15.0 }, "batch_long_context": { "input": 5.0, "_unit": "per 1M tokens", "cached_input": 0.5, "output": 22.5 }, "flex": { "input": 2.5, "_unit": "per 1M tokens", "cached_input": 0.25, "output": 15.0 }, "flex_long_context": { "input": 5.0, "_unit": "per 1M tokens", "cached_input": 0.5, "output": 22.5 }, "fast": { "input": 12.5, "_unit": "per 1M tokens", "cached_input": 1.25, "output": 75.0 }, "model_page:Text tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Cached input": { "price": 0.5, "unit": "1M tokens" }, "Output": { "price": 30.0, "unit": "1M tokens" } }, "notes": [ "For GPT-5.5, prompts with >272K input tokens are priced at 2x input and 1.5x output for the full session for standard, batch, and flex.", "Regional processing (data residency) endpoints are charged a 10% uplift for GPT-5.5." ] }, "rate_limits": { "documented_tiers": { "Standard": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } }, "Long Context": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": "272K input tokens", "tiers": { "Tier 1": { "RPM": 200, "TPM": 400000, "Batch queue limit": 5000000 }, "Tier 2": { "RPM": 500, "TPM": 1000000, "Batch queue limit": 40000000 }, "Tier 3": { "RPM": 1000, "TPM": 2000000, "Batch queue limit": 80000000 }, "Tier 4": { "RPM": 2000, "TPM": 10000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 8000, "TPM": 20000000, "Batch queue limit": 2000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.5", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1776824847, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-5.5 is a flagship model for the most complex professional work. Learn more in our [GPT-5.5 model guidance](/api/docs/guides/latest-model?model=gpt-5.5). Reasoning.effort supports: none, low, medium (default), high and xhigh.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "POST /v1/responses ('Reply with OK.', max_output_tokens 16) -> 200, model echoed: gpt-5.5-2026-04-23", "post_responses": { "status": 200, "request": { "model": "gpt-5.5", "input": "Reply with OK.", "max_output_tokens": 16, "reasoning": { "effort": "none" } }, "model_echo": "gpt-5.5-2026-04-23", "status_field": "completed", "incomplete_reason": null, "service_tier": "default", "usage": { "input_tokens": 10, "input_tokens_details": { "cache_write_tokens": 0, "cached_tokens": 0 }, "output_tokens": 5, "output_tokens_details": { "reasoning_tokens": 0 }, "total_tokens": 15 }, "reasoning_tokens": 0, "output_text": "OK", "est_cost_usd": 0.0002 } }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.5", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.5-2026-04-23", "record_kind": "snapshot", "canonical_model": "gpt-5.5", "display_name": "GPT-5.5 (snapshot gpt-5.5-2026-04-23)", "description": "A new class of intelligence for coding and professional work.", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5.5-2026-04-23", "family": "gpt-5.5", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-04-23", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2025-12-01", "context_window": 1050000, "max_input": null, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "none", "low", "medium", "high", "xhigh" ], "reasoning_effort_default": "medium", "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": true, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": true, "tool_hosted_shell": true, "tool_apply_patch": true, "tool_skills": true, "tool_tool_search": true, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "apply_patch", "code_interpreter", "computer_use", "file_search", "function_calling", "hosted_shell", "image_generation", "mcp", "skills", "tool_search", "web_search" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 5.0, "_unit": "per 1M tokens", "cached_input": 0.5, "output": 30.0 }, "standard_long_context": { "input": 10.0, "_unit": "per 1M tokens", "cached_input": 1.0, "output": 45.0 }, "batch": { "input": 2.5, "_unit": "per 1M tokens", "cached_input": 0.25, "output": 15.0 }, "batch_long_context": { "input": 5.0, "_unit": "per 1M tokens", "cached_input": 0.5, "output": 22.5 }, "flex": { "input": 2.5, "_unit": "per 1M tokens", "cached_input": 0.25, "output": 15.0 }, "flex_long_context": { "input": 5.0, "_unit": "per 1M tokens", "cached_input": 0.5, "output": 22.5 }, "fast": { "input": 12.5, "_unit": "per 1M tokens", "cached_input": 1.25, "output": 75.0 }, "model_page:Text tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Cached input": { "price": 0.5, "unit": "1M tokens" }, "Output": { "price": 30.0, "unit": "1M tokens" } }, "notes": [ "For GPT-5.5, prompts with >272K input tokens are priced at 2x input and 1.5x output for the full session for standard, batch, and flex.", "Regional processing (data residency) endpoints are charged a 10% uplift for GPT-5.5." ] }, "rate_limits": { "documented_tiers": { "Standard": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } }, "Long Context": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": "272K input tokens", "tiers": { "Tier 1": { "RPM": 200, "TPM": 400000, "Batch queue limit": 5000000 }, "Tier 2": { "RPM": 500, "TPM": 1000000, "Batch queue limit": 40000000 }, "Tier 3": { "RPM": 1000, "TPM": 2000000, "Batch queue limit": 80000000 }, "Tier 4": { "RPM": 2000, "TPM": 10000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 8000, "TPM": 20000000, "Batch queue limit": 2000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.5", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1776839241, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.5", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.5-cyber", "record_kind": "id_only", "canonical_model": "gpt-5.5-cyber", "display_name": "gpt-5.5-cyber", "description": "Cybersecurity model listed on the pricing page (Daybreak).", "aliases": [], "snapshots": [], "default_snapshot": null, "family": "cyber-daybreak", "status": [ "DOCUMENTED", "ACCOUNT_RESTRICTED" ], "flags": [ "NO_MODEL_PAGE" ], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "standard": { "input": 12.5, "_unit": "per 1M tokens", "cached_input": 1.25, "output": 75.0 } }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": "Daybreak program (pricing page only)", "availability": { "account": "Daybreak program (pricing page only)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "restricted", "http_status": 404, "request_note": "GET /v1/models/gpt-5.5-cyber -> 404 model_not_found", "get_model": { "status": 404, "error_type": "invalid_request_error", "error_code": "model_not_found", "error_message": "The model 'gpt-5.5-cyber' does not exist" } }, "sources": [ { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.5-pro", "record_kind": "model", "canonical_model": "gpt-5.5-pro", "display_name": "GPT-5.5 Pro", "description": "Version of GPT-5.5 that produces smarter and more precise responses.", "aliases": [], "snapshots": [ "gpt-5.5-pro-2026-04-23" ], "default_snapshot": "gpt-5.5-pro-2026-04-23", "family": "gpt-5.5", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-04-24", "release_date_source": "changelog", "knowledge_cutoff": "2025-12-01", "context_window": 1050000, "max_input": null, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "medium", "high", "xhigh" ], "reasoning_effort_default": "high", "reasoning_mode_pro": false, "streaming": false, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": true, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": true, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "hosted_shell", "image_generation", "mcp", "web_search" ], "features_documented": [ "file_search", "function_calling", "image_generation", "image_input", "mcp", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 30.0, "_unit": "per 1M tokens", "output": 180.0 }, "standard_long_context": { "input": 60.0, "_unit": "per 1M tokens", "output": 270.0 }, "batch": { "input": 15.0, "_unit": "per 1M tokens", "output": 90.0 }, "flex": { "input": 15.0, "_unit": "per 1M tokens", "output": 90.0 }, "model_page:Text tokens": { "Input": { "price": 30.0, "unit": "1M tokens" }, "Output": { "price": 180.0, "unit": "1M tokens" } }, "notes": [ "GPT-5.5 Pro does not offer a cached input discount.", "Regional processing (data residency) endpoints are charged a 10% uplift for GPT-5.5 Pro." ] }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 50, "TPM": 50000, "Batch queue limit": 500000 }, "Tier 2": { "RPM": 500, "TPM": 200000, "Batch queue limit": 1000000 }, "Tier 3": { "RPM": 500, "TPM": 500000, "Batch queue limit": 10000000 }, "Tier 4": { "RPM": 1000, "TPM": 1000000, "Batch queue limit": 20000000 }, "Tier 5": { "RPM": 2000, "TPM": 4000000, "Batch queue limit": 1500000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.5-pro", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1776894349, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-5.5 Pro uses more compute to think harder and provide consistently better answers. GPT-5.5 Pro is available for Responses API requests, including through the Batch API, to enable support for multi-turn model interactions before responding to API requests and other advanced API features in the future. Since GPT-5.5 Pro is designed to tackle tough problems, some requests may take several minutes to finish. To avoid timeouts, try using [background mode](/api/docs/guides/background). Reasoning.effort supports: medium, high (default) and xhigh.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.5-pro", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.5-pro-2026-04-23", "record_kind": "snapshot", "canonical_model": "gpt-5.5-pro", "display_name": "GPT-5.5 Pro (snapshot gpt-5.5-pro-2026-04-23)", "description": "Version of GPT-5.5 that produces smarter and more precise responses.", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5.5-pro-2026-04-23", "family": "gpt-5.5", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-04-23", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2025-12-01", "context_window": 1050000, "max_input": null, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "medium", "high", "xhigh" ], "reasoning_effort_default": "high", "reasoning_mode_pro": false, "streaming": false, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": true, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": true, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": true }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "hosted_shell", "image_generation", "mcp", "web_search" ], "features_documented": [ "file_search", "function_calling", "image_generation", "image_input", "mcp", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 30.0, "_unit": "per 1M tokens", "output": 180.0 }, "standard_long_context": { "input": 60.0, "_unit": "per 1M tokens", "output": 270.0 }, "batch": { "input": 15.0, "_unit": "per 1M tokens", "output": 90.0 }, "flex": { "input": 15.0, "_unit": "per 1M tokens", "output": 90.0 }, "model_page:Text tokens": { "Input": { "price": 30.0, "unit": "1M tokens" }, "Output": { "price": 180.0, "unit": "1M tokens" } }, "notes": [ "GPT-5.5 Pro does not offer a cached input discount.", "Regional processing (data residency) endpoints are charged a 10% uplift for GPT-5.5 Pro." ] }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 50, "TPM": 50000, "Batch queue limit": 500000 }, "Tier 2": { "RPM": 500, "TPM": 200000, "Batch queue limit": 1000000 }, "Tier 3": { "RPM": 500, "TPM": 500000, "Batch queue limit": 10000000 }, "Tier 4": { "RPM": 1000, "TPM": 1000000, "Batch queue limit": 20000000 }, "Tier 5": { "RPM": 2000, "TPM": 4000000, "Batch queue limit": 1500000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.5-pro", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1776894470, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.5-pro", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.6", "record_kind": "alias", "canonical_model": "gpt-5.6-sol", "display_name": "GPT-5.6 Sol (alias gpt-5.6)", "description": "Flagship model for complex professional work", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5.6-sol", "family": "gpt-5.6", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [ "ALIAS_WORKS_ON_POST_BUT_404_ON_GET_MODELS" ], "release_date": "2026-07-09", "release_date_source": "changelog (parent model)", "knowledge_cutoff": "2026-02-16", "context_window": 1050000, "max_input": 922000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "none", "low", "medium", "high", "xhigh", "max" ], "reasoning_effort_default": "medium", "reasoning_mode_pro": true, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": true, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": true, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": true, "tool_hosted_shell": true, "tool_apply_patch": true, "tool_skills": true, "tool_tool_search": true, "tool_function_calling": false, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "apply_patch", "code_interpreter", "computer_use", "file_search", "hosted_shell", "image_generation", "mcp", "skills", "tool_search", "web_search" ], "features_documented": [ "file_search", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 4.0, "_unit": "per 1M tokens", "cached_input": 0.4, "cache_write": 5.0, "output": 20.0 }, "standard_long_context": { "input": 8.0, "_unit": "per 1M tokens", "cached_input": 0.8, "cache_write": 10.0, "output": 30.0 }, "batch": { "input": 2.0, "_unit": "per 1M tokens", "cached_input": 0.2, "cache_write": 2.5, "output": 10.0 }, "batch_long_context": { "input": 4.0, "_unit": "per 1M tokens", "cached_input": 0.4, "cache_write": 5.0, "output": 15.0 }, "flex": { "input": 2.0, "_unit": "per 1M tokens", "cached_input": 0.2, "cache_write": 2.5, "output": 10.0 }, "flex_long_context": { "input": 4.0, "_unit": "per 1M tokens", "cached_input": 0.4, "cache_write": 5.0, "output": 15.0 }, "fast": { "input": 8.0, "_unit": "per 1M tokens", "cached_input": 0.8, "cache_write": 10.0, "output": 40.0 }, "fast_long_context": { "input": 16.0, "_unit": "per 1M tokens", "cached_input": 1.6, "cache_write": 20.0, "output": 60.0 }, "model_page:Text tokens": { "Input": { "price": 4.0, "unit": "1M tokens" }, "Cached input": { "price": 0.4, "unit": "1M tokens" }, "Output": { "price": 20.0, "unit": "1M tokens" } }, "notes": [ "GPT-5.6 Sol costs $4 per million input tokens and $20 per million output tokens, a 20% reduction in input pricing and a 33% reduction in output pricing. GPT-5.6 Sol’s promotional pricing is available at least through November 21, 2026.", "Prompts with >272K input tokens are priced at 2x input and 1.5x output for the full request.", "Cache writes are billed at 1.25x the uncached input token rate." ] }, "rate_limits": { "documented_tiers": { "Standard": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.6-sol", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "POST /v1/responses ('Reply with OK.', max_output_tokens 16) -> 200, model echoed: gpt-5.6-sol", "get_model": { "status": 404, "error_type": "invalid_request_error", "error_code": "model_not_found", "error_message": "The model 'gpt-5.6' does not exist" }, "post_responses": { "status": 200, "request": { "model": "gpt-5.6", "input": "Reply with OK.", "max_output_tokens": 16, "reasoning": { "effort": "none" } }, "model_echo": "gpt-5.6-sol", "status_field": "completed", "service_tier": "default", "usage": { "input_tokens": 10, "input_tokens_details": { "cache_write_tokens": 0, "cached_tokens": 0 }, "output_tokens": 5, "output_tokens_details": { "reasoning_tokens": 0 }, "total_tokens": 15 }, "output_text": "OK", "est_cost_usd": 0.00014 } }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.6-sol", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.6-cyber", "record_kind": "model", "canonical_model": "gpt-5.6-cyber", "display_name": "GPT-5.6 Cyber", "description": "Our most advanced cybersecurity model for authorized vulnerability research and security testing.", "aliases": [ "gpt-daybreak-red-latest" ], "snapshots": [], "default_snapshot": "gpt-5.6-cyber", "family": "cyber-daybreak", "status": [ "DOCUMENTED", "ACCOUNT_RESTRICTED" ], "flags": [], "release_date": "2026-08-07", "release_date_source": "changelog", "knowledge_cutoff": "2026-02-16", "context_window": 400000, "max_input": 272000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": true, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": true, "tool_hosted_shell": true, "tool_apply_patch": true, "tool_skills": true, "tool_tool_search": true, "tool_function_calling": false, "web_search_feature": true }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" } ], "tools": [ "apply_patch", "code_interpreter", "computer_use", "file_search", "hosted_shell", "image_generation", "mcp", "skills", "tool_search", "web_search" ], "features_documented": [ "file_search", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 12.5, "_unit": "per 1M tokens", "cached_input": 1.25, "cache_write": 15.625, "output": 75.0 }, "model_page:Text tokens": { "Input": { "price": 12.5, "unit": "1M tokens" }, "Cached input": { "price": 1.25, "unit": "1M tokens" }, "Output": { "price": 75.0, "unit": "1M tokens" } }, "notes": [ "Prompts with >272K input tokens are priced at 2x input and 1.5x output for the full request.", "Cache writes are billed at 1.25x the uncached input token rate." ] }, "rate_limits": { "documented_tiers": { "Standard": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.6-cyber", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": "Daybreak program (separate approval and provisioning) — https://openai.com/daybreak/", "availability": { "account": "Daybreak program (separate approval and provisioning) — https://openai.com/daybreak/", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "An alias for our most advanced purpose-trained cybersecurity models, for approved defenders conducting advanced, authorized vulnerability research, exploit validation, and security testing. This model requires separate approval and provisioning, you can apply to join the Daybreak program [here](https://openai.com/daybreak/). More details on pricing [here](https://developers.openai.com/api/docs/pricing).", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "restricted", "http_status": 404, "request_note": "GET /v1/models/gpt-5.6-cyber -> 404 model_not_found", "get_model": { "status": 404, "error_type": "invalid_request_error", "error_code": "model_not_found", "error_message": "The model 'gpt-5.6-cyber' does not exist" } }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.6-cyber", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.6-luna", "record_kind": "model", "canonical_model": "gpt-5.6-luna", "display_name": "GPT-5.6 Luna", "description": "GPT-5.6 model optimized for cost-sensitive workloads", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5.6-luna", "family": "gpt-5.6", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-07-09", "release_date_source": "changelog", "knowledge_cutoff": "2026-02-16", "context_window": 1050000, "max_input": 922000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "none", "low", "medium", "high", "xhigh", "max" ], "reasoning_effort_default": "medium", "reasoning_mode_pro": true, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": true, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": true, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": true, "tool_hosted_shell": true, "tool_apply_patch": true, "tool_skills": true, "tool_tool_search": true, "tool_function_calling": false, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "apply_patch", "code_interpreter", "computer_use", "file_search", "hosted_shell", "image_generation", "mcp", "skills", "tool_search", "web_search" ], "features_documented": [ "file_search", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 0.2, "_unit": "per 1M tokens", "cached_input": 0.02, "cache_write": 0.25, "output": 1.2 }, "standard_long_context": { "input": 0.4, "_unit": "per 1M tokens", "cached_input": 0.04, "cache_write": 0.5, "output": 1.8 }, "batch": { "input": 0.1, "_unit": "per 1M tokens", "cached_input": 0.01, "cache_write": 0.125, "output": 0.6 }, "batch_long_context": { "input": 0.2, "_unit": "per 1M tokens", "cached_input": 0.02, "cache_write": 0.25, "output": 0.9 }, "flex": { "input": 0.1, "_unit": "per 1M tokens", "cached_input": 0.01, "cache_write": 0.125, "output": 0.6 }, "flex_long_context": { "input": 0.2, "_unit": "per 1M tokens", "cached_input": 0.02, "cache_write": 0.25, "output": 0.9 }, "fast": { "input": 0.4, "_unit": "per 1M tokens", "cached_input": 0.04, "cache_write": 0.5, "output": 2.4 }, "fast_long_context": { "input": 0.8, "_unit": "per 1M tokens", "cached_input": 0.08, "cache_write": 1.0, "output": 3.6 }, "model_page:Text tokens": { "Input": { "price": 0.2, "unit": "1M tokens" }, "Cached input": { "price": 0.02, "unit": "1M tokens" }, "Output": { "price": 1.2, "unit": "1M tokens" } }, "notes": [ "Prompts with >272K input tokens are priced at 2x input and 1.5x output for the full request.", "Cache writes are billed at 1.25x the uncached input token rate." ] }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 5000000 }, "Tier 2": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "TPM": 180000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.6-luna", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1782228658, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-5.6 Luna is designed for cost-sensitive, high-volume workloads. It roughly corresponds to the nano model tier used in earlier GPT-5 families. Reasoning.effort supports: none, low, medium (default), high, xhigh, and max.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "POST /v1/responses ('Reply with OK.', max_output_tokens 16) -> 200, model echoed: gpt-5.6-luna", "get_model": { "status": 200, "id": "gpt-5.6-luna", "object": "model", "created": 1782228658, "owned_by": "system", "shutdown_date": null }, "post_responses": { "status": 200, "request": { "model": "gpt-5.6-luna", "input": "Reply with OK.", "max_output_tokens": 16, "reasoning": { "effort": "none" } }, "model_echo": "gpt-5.6-luna", "status_field": "completed", "incomplete_reason": null, "service_tier": "default", "usage": { "input_tokens": 10, "input_tokens_details": { "cache_write_tokens": 0, "cached_tokens": 0 }, "output_tokens": 5, "output_tokens_details": { "reasoning_tokens": 0 }, "total_tokens": 15 }, "reasoning_tokens": 0, "output_text": "OK", "est_cost_usd": 8e-06 } }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.6-luna", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.6-sol", "record_kind": "model", "canonical_model": "gpt-5.6-sol", "display_name": "GPT-5.6 Sol", "description": "Flagship model for complex professional work", "aliases": [ "gpt-5.6", "gpt-daybreak-blue-latest" ], "snapshots": [], "default_snapshot": "gpt-5.6-sol", "family": "gpt-5.6", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-07-09", "release_date_source": "changelog", "knowledge_cutoff": "2026-02-16", "context_window": 1050000, "max_input": 922000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "none", "low", "medium", "high", "xhigh", "max" ], "reasoning_effort_default": "medium", "reasoning_mode_pro": true, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": true, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": true, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": true, "tool_hosted_shell": true, "tool_apply_patch": true, "tool_skills": true, "tool_tool_search": true, "tool_function_calling": false, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "apply_patch", "code_interpreter", "computer_use", "file_search", "hosted_shell", "image_generation", "mcp", "skills", "tool_search", "web_search" ], "features_documented": [ "file_search", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 4.0, "_unit": "per 1M tokens", "cached_input": 0.4, "cache_write": 5.0, "output": 20.0 }, "standard_long_context": { "input": 8.0, "_unit": "per 1M tokens", "cached_input": 0.8, "cache_write": 10.0, "output": 30.0 }, "batch": { "input": 2.0, "_unit": "per 1M tokens", "cached_input": 0.2, "cache_write": 2.5, "output": 10.0 }, "batch_long_context": { "input": 4.0, "_unit": "per 1M tokens", "cached_input": 0.4, "cache_write": 5.0, "output": 15.0 }, "flex": { "input": 2.0, "_unit": "per 1M tokens", "cached_input": 0.2, "cache_write": 2.5, "output": 10.0 }, "flex_long_context": { "input": 4.0, "_unit": "per 1M tokens", "cached_input": 0.4, "cache_write": 5.0, "output": 15.0 }, "fast": { "input": 8.0, "_unit": "per 1M tokens", "cached_input": 0.8, "cache_write": 10.0, "output": 40.0 }, "fast_long_context": { "input": 16.0, "_unit": "per 1M tokens", "cached_input": 1.6, "cache_write": 20.0, "output": 60.0 }, "model_page:Text tokens": { "Input": { "price": 4.0, "unit": "1M tokens" }, "Cached input": { "price": 0.4, "unit": "1M tokens" }, "Output": { "price": 20.0, "unit": "1M tokens" } }, "notes": [ "GPT-5.6 Sol costs $4 per million input tokens and $20 per million output tokens, a 20% reduction in input pricing and a 33% reduction in output pricing. GPT-5.6 Sol’s promotional pricing is available at least through November 21, 2026.", "Prompts with >272K input tokens are priced at 2x input and 1.5x output for the full request.", "Cache writes are billed at 1.25x the uncached input token rate." ] }, "rate_limits": { "documented_tiers": { "Standard": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.6-sol", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1782228018, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-5.6 Sol is a flagship model in the GPT-5.6 family. It roughly corresponds to the unsuffixed model tier used in earlier GPT-5 families. The `gpt-5.6` alias routes requests to GPT-5.6 Sol. Reasoning.effort supports: none, low, medium (default), high, xhigh, and max.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "POST /v1/responses ('Reply with OK.', max_output_tokens 16) -> 200, model echoed: gpt-5.6-sol", "post_responses": { "status": 200, "request": { "model": "gpt-5.6-sol", "input": "Reply with OK.", "max_output_tokens": 16, "reasoning": { "effort": "none" } }, "model_echo": "gpt-5.6-sol", "status_field": "completed", "incomplete_reason": null, "service_tier": "default", "usage": { "input_tokens": 10, "input_tokens_details": { "cache_write_tokens": 0, "cached_tokens": 0 }, "output_tokens": 5, "output_tokens_details": { "reasoning_tokens": 0 }, "total_tokens": 15 }, "reasoning_tokens": 0, "output_text": "OK", "est_cost_usd": 0.00014 } }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.6-sol", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-5.6-terra", "record_kind": "model", "canonical_model": "gpt-5.6-terra", "display_name": "GPT-5.6 Terra", "description": "GPT-5.6 model that balances intelligence and cost", "aliases": [], "snapshots": [], "default_snapshot": "gpt-5.6-terra", "family": "gpt-5.6", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-07-09", "release_date_source": "changelog", "knowledge_cutoff": "2026-02-16", "context_window": 1050000, "max_input": 922000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "none", "low", "medium", "high", "xhigh", "max" ], "reasoning_effort_default": "medium", "reasoning_mode_pro": true, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": true, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": true, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": true, "tool_hosted_shell": true, "tool_apply_patch": true, "tool_skills": true, "tool_tool_search": true, "tool_function_calling": false, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "apply_patch", "code_interpreter", "computer_use", "file_search", "hosted_shell", "image_generation", "mcp", "skills", "tool_search", "web_search" ], "features_documented": [ "file_search", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 2.0, "_unit": "per 1M tokens", "cached_input": 0.2, "cache_write": 2.5, "output": 12.0 }, "standard_long_context": { "input": 4.0, "_unit": "per 1M tokens", "cached_input": 0.4, "cache_write": 5.0, "output": 18.0 }, "batch": { "input": 1.0, "_unit": "per 1M tokens", "cached_input": 0.1, "cache_write": 1.25, "output": 6.0 }, "batch_long_context": { "input": 2.0, "_unit": "per 1M tokens", "cached_input": 0.2, "cache_write": 2.5, "output": 9.0 }, "flex": { "input": 1.0, "_unit": "per 1M tokens", "cached_input": 0.1, "cache_write": 1.25, "output": 6.0 }, "flex_long_context": { "input": 2.0, "_unit": "per 1M tokens", "cached_input": 0.2, "cache_write": 2.5, "output": 9.0 }, "fast": { "input": 4.0, "_unit": "per 1M tokens", "cached_input": 0.4, "cache_write": 5.0, "output": 24.0 }, "fast_long_context": { "input": 8.0, "_unit": "per 1M tokens", "cached_input": 0.8, "cache_write": 10.0, "output": 36.0 }, "model_page:Text tokens": { "Input": { "price": 2.0, "unit": "1M tokens" }, "Cached input": { "price": 0.2, "unit": "1M tokens" }, "Output": { "price": 12.0, "unit": "1M tokens" } }, "notes": [ "Prompts with >272K input tokens are priced at 2x input and 1.5x output for the full request.", "Cache writes are billed at 1.25x the uncached input token rate." ] }, "rate_limits": { "documented_tiers": { "Standard": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-5.6-terra", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1782228459, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-5.6 Terra is designed for workloads that balance intelligence and cost. It roughly corresponds to the mini model tier used in earlier GPT-5 families. Reasoning.effort supports: none, low, medium (default), high, xhigh, and max.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "POST /v1/responses ('Reply with OK.', max_output_tokens 16) -> 200, model echoed: gpt-5.6-terra", "post_responses": { "status": 200, "request": { "model": "gpt-5.6-terra", "input": "Reply with OK.", "max_output_tokens": 16, "reasoning": { "effort": "none" } }, "model_echo": "gpt-5.6-terra", "status_field": "completed", "incomplete_reason": null, "service_tier": "default", "usage": { "input_tokens": 10, "input_tokens_details": { "cache_write_tokens": 0, "cached_tokens": 0 }, "output_tokens": 5, "output_tokens_details": { "reasoning_tokens": 0 }, "total_tokens": 15 }, "reasoning_tokens": 0, "output_text": "OK", "est_cost_usd": 8e-05 } }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-5.6-terra", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-6-astra", "record_kind": "model", "canonical_model": "gpt-6-astra", "display_name": "GPT-6 Astra", "description": "Our most capable model, built for the hardest end-to-end work", "aliases": [], "snapshots": [], "default_snapshot": "gpt-6-astra", "family": "gpt-6", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-09-03", "release_date_source": "changelog", "knowledge_cutoff": "2026-04-30", "context_window": 1050000, "max_input": 922000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "low", "medium", "high", "xhigh", "max" ], "reasoning_effort_default": null, "reasoning_mode_pro": "unknown", "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": true, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": true, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": true, "tool_hosted_shell": true, "tool_apply_patch": true, "tool_skills": true, "tool_tool_search": true, "tool_function_calling": false, "web_search_feature": true }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "apply_patch", "code_interpreter", "computer_use", "file_search", "hosted_shell", "image_generation", "mcp", "skills", "tool_search", "web_search" ], "features_documented": [ "file_search", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "standard": { "input": 10.0, "_unit": "per 1M tokens", "cached_input": 1.0, "cache_write": 12.5, "output": 50.0 }, "standard_long_context": { "input": 20.0, "_unit": "per 1M tokens", "cached_input": 2.0, "cache_write": 25.0, "output": 75.0 }, "batch": { "input": 5.0, "_unit": "per 1M tokens", "cached_input": 0.5, "cache_write": 6.25, "output": 25.0 }, "batch_long_context": { "input": 10.0, "_unit": "per 1M tokens", "cached_input": 1.0, "cache_write": 12.5, "output": 37.5 }, "flex": { "input": 5.0, "_unit": "per 1M tokens", "cached_input": 0.5, "cache_write": 6.25, "output": 25.0 }, "flex_long_context": { "input": 10.0, "_unit": "per 1M tokens", "cached_input": 1.0, "cache_write": 12.5, "output": 37.5 }, "fast": { "input": 20.0, "_unit": "per 1M tokens", "cached_input": 2.0, "cache_write": 25.0, "output": 100.0 }, "fast_long_context": { "input": 40.0, "_unit": "per 1M tokens", "cached_input": 4.0, "cache_write": 50.0, "output": 150.0 }, "model_page:Text tokens": { "Input": { "price": 10.0, "unit": "1M tokens" }, "Cached input": { "price": 1.0, "unit": "1M tokens" }, "Cache writes": { "price": 12.5, "unit": "1M tokens" }, "Output": { "price": 50.0, "unit": "1M tokens" } }, "notes": [ "Prompts with more than 272K input tokens are priced at 2x input and cache rates and 1.5x output for the full request.", "Cache writes are billed at 1.25x the uncached input token rate.", "Batch and Flex are priced at 50% of Standard rates. Fast mode is priced at 2x the applicable rates." ] }, "rate_limits": { "documented_tiers": { "Standard": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-6-astra", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1787853604, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-6 Astra is our most capable model, built for the hardest end-to-end work. Use it for complex reasoning, coding, computer use, research, and document creation. `reasoning.effort` supports `low`, `medium`, `high`, `xhigh`, and `max`. Get started with GPT-6 Astra using the [model guide](/api/docs/guides/latest-model?model=gpt-6-astra).", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "POST /v1/responses ('Reply with OK.', max_output_tokens 16) -> 200, model echoed: gpt-6-astra", "get_model": { "status": 200, "id": "gpt-6-astra", "object": "model", "created": 1787853604, "owned_by": "system", "shutdown_date": null }, "post_responses": { "status": 200, "request": { "model": "gpt-6-astra", "input": "Reply with OK.", "max_output_tokens": 16, "reasoning": { "effort": "low" } }, "model_echo": "gpt-6-astra", "status_field": "completed", "incomplete_reason": null, "service_tier": "default", "usage": { "input_tokens": 10, "input_tokens_details": { "cache_write_tokens": 0, "cached_tokens": 0 }, "output_tokens": 5, "output_tokens_details": { "reasoning_tokens": 0 }, "total_tokens": 15 }, "reasoning_tokens": 0, "output_text": "OK", "est_cost_usd": 0.00035 } }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-6-astra", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-audio", "record_kind": "model", "canonical_model": "gpt-audio", "display_name": "GPT-Audio", "description": "For audio inputs and outputs with Chat Completions API", "aliases": [], "snapshots": [ "gpt-audio-2025-08-28" ], "default_snapshot": "gpt-audio-2025-08-28", "family": "audio-chat", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-08-28", "release_date_source": "changelog", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" } ], "tools": [], "features_documented": [ "function_calling", "streaming" ], "pricing": { "standard": { "audio_input": 32.0, "_unit": "per 1M tokens", "audio_output": 64.0, "text_input": 2.5, "text_output": 10.0 }, "model_page:Text tokens": { "Input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 32.0, "unit": "1M tokens" }, "Output": { "price": 64.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 2000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-audio", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1756339249, "openapi_enum": false }, "deprecation": [ { "announced": "2026-07-20", "shutdown_date": "2027-01-20", "replacement": "`gpt-audio-1.5`", "phase": "upcoming", "section": "2026-07-20: Legacy audio, realtime, and transcription models", "source": "https://developers.openai.com/api/docs/deprecations#2026-07-20-legacy-audio-realtime-and-transcription-models" }, { "announced": null, "shutdown_date": "2027-01-20", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2027-01-20", "intro": "The gpt-audio model is our first generally available audio model. It accepts audio inputs and outputs, and can be used in the Chat Completions REST API.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-audio", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-07-20-legacy-audio-realtime-and-transcription-models", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-audio-1.5", "record_kind": "model", "canonical_model": "gpt-audio-1.5", "display_name": "GPT-Audio-1.5", "description": "The best voice model for audio in, audio out with Chat Completions.", "aliases": [], "snapshots": [], "default_snapshot": "gpt-audio-1.5", "family": "audio-chat", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-02-23", "release_date_source": "changelog", "knowledge_cutoff": "2024-09-30", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" } ], "tools": [], "features_documented": [ "function_calling", "streaming" ], "pricing": { "standard": { "audio_input": 32.0, "_unit": "per 1M tokens", "audio_output": 64.0, "text_input": 2.5, "text_output": 10.0 }, "model_page:Text tokens": { "Input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 32.0, "unit": "1M tokens" }, "Output": { "price": 64.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 2000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-audio-1.5", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1771550885, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "The gpt-audio model is our first generally available audio model. It accepts audio inputs and outputs, and can be used in the Chat Completions REST API.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-audio-1.5", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-audio-2025-08-28", "record_kind": "snapshot", "canonical_model": "gpt-audio", "display_name": "GPT-Audio (snapshot gpt-audio-2025-08-28)", "description": "For audio inputs and outputs with Chat Completions API", "aliases": [], "snapshots": [], "default_snapshot": "gpt-audio-2025-08-28", "family": "audio-chat", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-08-28", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" } ], "tools": [], "features_documented": [ "function_calling", "streaming" ], "pricing": { "standard": { "audio_input": 32.0, "_unit": "per 1M tokens", "audio_output": 64.0, "text_input": 2.5, "text_output": 10.0 }, "model_page:Text tokens": { "Input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 32.0, "unit": "1M tokens" }, "Output": { "price": 64.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 2000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-audio", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1756256146, "openapi_enum": false }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-audio", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-audio-mini", "record_kind": "model", "canonical_model": "gpt-audio-mini", "display_name": "GPT-Audio Mini", "description": "A cost-efficient version of GPT Audio", "aliases": [], "snapshots": [ "gpt-audio-mini-2025-10-06", "gpt-audio-mini-2025-12-15" ], "default_snapshot": "gpt-audio-mini-2025-12-15", "family": "audio-chat", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-10-06", "release_date_source": "changelog", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" } ], "tools": [ "function_calling" ], "features_documented": [ "function_calling", "prompt_caching" ], "pricing": { "standard": { "audio_input": 10.0, "_unit": "per 1M tokens", "audio_output": 20.0, "text_input": 0.6, "text_output": 2.4 }, "model_page:Text tokens": { "Input": { "price": 0.6, "unit": "1M tokens" }, "Output": { "price": 2.4, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000 }, "Tier 2": { "RPM": 5000, "TPM": 450000 }, "Tier 3": { "RPM": 5000, "TPM": 800000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-audio-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1759512027, "openapi_enum": true }, "deprecation": [ { "announced": "2026-07-20", "shutdown_date": "2027-01-20", "replacement": "`gpt-audio-1.5`", "phase": "upcoming", "section": "2026-07-20: Legacy audio, realtime, and transcription models", "source": "https://developers.openai.com/api/docs/deprecations#2026-07-20-legacy-audio-realtime-and-transcription-models" }, { "announced": null, "shutdown_date": "2027-01-20", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2027-01-20", "intro": "A cost-efficient version of GPT Audio. It accepts audio inputs and outputs, and can be used in the Chat Completions REST API.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-audio-mini", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-07-20-legacy-audio-realtime-and-transcription-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-audio-mini-2025-10-06", "record_kind": "snapshot", "canonical_model": "gpt-audio-mini", "display_name": "GPT-Audio Mini (snapshot gpt-audio-mini-2025-10-06)", "description": "A cost-efficient version of GPT Audio", "aliases": [], "snapshots": [], "default_snapshot": "gpt-audio-mini-2025-12-15", "family": "audio-chat", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "RETIRED" ], "flags": [ "STILL_LISTED_AFTER_DOCUMENTED_SHUTDOWN" ], "release_date": "2025-10-06", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" } ], "tools": [ "function_calling" ], "features_documented": [ "function_calling", "prompt_caching" ], "pricing": { "standard": { "audio_input": 10.0, "_unit": "per 1M tokens", "audio_output": 20.0, "text_input": 0.6, "text_output": 2.4 }, "model_page:Text tokens": { "Input": { "price": 0.6, "unit": "1M tokens" }, "Output": { "price": 2.4, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000 }, "Tier 2": { "RPM": 5000, "TPM": 450000 }, "Tier 3": { "RPM": 5000, "TPM": 800000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-audio-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1759512137, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-07-23", "replacement": "`gpt-audio-1.5`", "phase": "past", "section": "2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown" }, { "announced": null, "shutdown_date": "2026-07-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-07-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-audio-mini", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-audio-mini-2025-12-15", "record_kind": "snapshot", "canonical_model": "gpt-audio-mini", "display_name": "GPT-Audio Mini (snapshot gpt-audio-mini-2025-12-15)", "description": "A cost-efficient version of GPT Audio", "aliases": [], "snapshots": [], "default_snapshot": "gpt-audio-mini-2025-12-15", "family": "audio-chat", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-12-15", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 16384, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" } ], "tools": [ "function_calling" ], "features_documented": [ "function_calling", "prompt_caching" ], "pricing": { "standard": { "audio_input": 10.0, "_unit": "per 1M tokens", "audio_output": 20.0, "text_input": 0.6, "text_output": 2.4 }, "model_page:Text tokens": { "Input": { "price": 0.6, "unit": "1M tokens" }, "Output": { "price": 2.4, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000 }, "Tier 2": { "RPM": 5000, "TPM": 450000 }, "Tier 3": { "RPM": 5000, "TPM": 800000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-audio-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1765760008, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-audio-mini", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-daybreak-blue-latest", "record_kind": "model", "canonical_model": "gpt-daybreak-blue-latest", "display_name": "Daybreak Blue", "description": "An alias for flagship general-purpose models with safeguards for defensive cybersecurity work.", "aliases": [ "gpt-5.6-sol" ], "snapshots": [], "default_snapshot": "gpt-5.6-sol", "family": "cyber-daybreak", "status": [ "DOCUMENTED", "ACCOUNT_RESTRICTED" ], "flags": [], "release_date": "2026-08-07", "release_date_source": "changelog", "knowledge_cutoff": "2026-02-16", "context_window": 1050000, "max_input": 922000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": true, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": true, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": true, "tool_hosted_shell": true, "tool_apply_patch": true, "tool_skills": true, "tool_tool_search": true, "tool_function_calling": false, "web_search_feature": true }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" } ], "tools": [ "apply_patch", "code_interpreter", "computer_use", "file_search", "hosted_shell", "image_generation", "mcp", "skills", "tool_search", "web_search" ], "features_documented": [ "file_search", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "documented_tiers": { "Standard": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-blue-latest", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": "Daybreak program (separate approval and provisioning) — https://openai.com/daybreak/", "availability": { "account": "Daybreak program (separate approval and provisioning) — https://openai.com/daybreak/", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "An alias for our flagship general-purpose models, with safeguards calibrated for defensive cybersecurity work. This model requires separate approval and provisioning, you can apply to join the Daybreak program [here](https://openai.com/daybreak/). More details on pricing [here](https://developers.openai.com/api/docs/pricing).", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "restricted", "http_status": 404, "request_note": "GET /v1/models/gpt-daybreak-blue-latest -> 404 model_not_found", "get_model": { "status": 404, "error_type": "invalid_request_error", "error_code": "model_not_found", "error_message": "The model 'gpt-daybreak-blue-latest' does not exist" } }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-daybreak-blue-latest", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-daybreak-red-latest", "record_kind": "model", "canonical_model": "gpt-daybreak-red-latest", "display_name": "Daybreak Red", "description": "An alias for advanced cybersecurity models for authorized vulnerability research and security testing.", "aliases": [ "gpt-5.6-cyber" ], "snapshots": [], "default_snapshot": "gpt-5.6-cyber", "family": "cyber-daybreak", "status": [ "DOCUMENTED" ], "flags": [], "release_date": "2026-08-07", "release_date_source": "changelog", "knowledge_cutoff": "2026-02-16", "context_window": 400000, "max_input": 272000, "max_output": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": true, "explicit_cache_breakpoints": true, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": true, "tool_hosted_shell": true, "tool_apply_patch": true, "tool_skills": true, "tool_tool_search": true, "tool_function_calling": false, "web_search_feature": true }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" } ], "tools": [ "apply_patch", "code_interpreter", "computer_use", "file_search", "hosted_shell", "image_generation", "mcp", "skills", "tool_search", "web_search" ], "features_documented": [ "file_search", "function_calling", "image_input", "prompt_caching", "streaming", "structured_outputs", "web_search" ], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "documented_tiers": { "Standard": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 500000, "Batch queue limit": 1500000 }, "Tier 2": { "RPM": 5000, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 3": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 15000, "TPM": 40000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-red-latest", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": "Daybreak program (separate approval and provisioning) — https://openai.com/daybreak/", "availability": { "account": "Daybreak program (separate approval and provisioning) — https://openai.com/daybreak/", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "An alias for our most advanced purpose-trained cybersecurity models, for approved defenders conducting advanced, authorized vulnerability research, exploit validation, and security testing. This model requires separate approval and provisioning, you can apply to join the Daybreak program [here](https://openai.com/daybreak/). More details on pricing [here](https://developers.openai.com/api/docs/pricing).", "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-daybreak-red-latest", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-image-1", "record_kind": "model", "canonical_model": "gpt-image-1", "display_name": "GPT-Image-1", "description": "Our previous image generation model", "aliases": [], "snapshots": [], "default_snapshot": "gpt-image-1", "family": "image", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-04-24", "release_date_source": "GET /v1/models created timestamp (approximation)", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "image" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": false, "image_in": true, "image_out": true, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": true, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": true, "image_edit_api": true, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": "unknown", "tool_file_search": "unknown", "tool_code_interpreter": "unknown", "tool_image_generation": "unknown", "tool_mcp": "unknown", "tool_computer_use": "unknown", "tool_hosted_shell": "unknown", "tool_apply_patch": "unknown", "tool_skills": "unknown", "tool_tool_search": "unknown", "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Image generation", "route": "/v1/images/generations" }, { "name": "Image edit", "route": "/v1/images/edits" } ], "tools": [], "features_documented": [ "inpainting" ], "pricing": { "standard": { "image_input": 10.0, "_unit": "per 1M tokens", "image_cached_input": 2.5, "image_output": 40.0, "text_input": 5.0, "text_cached_input": 1.25 }, "batch": { "image_input": 5.0, "_unit": "per 1M tokens", "image_cached_input": 1.25, "image_output": 20.0, "text_input": 2.5, "text_cached_input": 0.63 }, "model_page:Text tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Cached input": { "price": 1.25, "unit": "1M tokens" } }, "model_page:Image tokens": { "Input": { "price": 10.0, "unit": "1M tokens" }, "Cached input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 40.0, "unit": "1M tokens" } }, "model_page:Image generation": { "1024x1024": { "price": 0.167, "unit": "image" }, "1024x1536": { "price": 0.25, "unit": "image" }, "1536x1024": { "price": 0.25, "unit": "image" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "TPM", "IPM" ], "note": null, "tiers": { "Tier 1": { "TPM": 100000, "IPM": 5 }, "Tier 2": { "TPM": 250000, "IPM": 20 }, "Tier 3": { "TPM": 800000, "IPM": 50 }, "Tier 4": { "TPM": 3000000, "IPM": 150 }, "Tier 5": { "TPM": 8000000, "IPM": 250 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-image-1", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1745517030, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-image-2`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" }, { "announced": null, "shutdown_date": "2026-10-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-10-23", "intro": "GPT Image 1 is a natively multimodal language model that accepts both text and image inputs, and produces image outputs.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-image-1", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-image-1-mini", "record_kind": "model", "canonical_model": "gpt-image-1-mini", "display_name": "GPT-Image-1 Mini", "description": "A cost-efficient version of GPT Image 1", "aliases": [], "snapshots": [], "default_snapshot": "gpt-image-1-mini", "family": "image", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-10-06", "release_date_source": "changelog", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "image" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": false, "image_in": true, "image_out": true, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": "unknown", "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": true, "image_edit_api": true, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Batch", "route": "/v1/batch" }, { "name": "Image generation", "route": "/v1/images/generations" }, { "name": "Image edit", "route": "/v1/images/edits" } ], "tools": [], "features_documented": [], "pricing": { "standard": { "image_input": 2.5, "_unit": "per 1M tokens", "image_cached_input": 0.25, "image_output": 8.0, "text_input": 2.0, "text_cached_input": 0.2 }, "batch": { "image_input": 1.25, "_unit": "per 1M tokens", "image_cached_input": 0.13, "image_output": 4.0, "text_input": 1.0, "text_cached_input": 0.1 }, "model_page:Text tokens": { "Input": { "price": 2.0, "unit": "1M tokens" }, "Cached input": { "price": 0.2, "unit": "1M tokens" } }, "model_page:Image tokens": { "Input": { "price": 2.5, "unit": "1M tokens" }, "Cached input": { "price": 0.25, "unit": "1M tokens" }, "Output": { "price": 8.0, "unit": "1M tokens" } }, "model_page:Image generation": { "1024x1024": { "price": 0.036, "unit": "image" }, "1024x1536": { "price": 0.052, "unit": "image" }, "1536x1024": { "price": 0.052, "unit": "image" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "IPM", "TPM" ], "note": null, "tiers": { "Tier 1": { "IPM": 5, "TPM": 100000 }, "Tier 2": { "IPM": 20, "TPM": 250000 }, "Tier 3": { "IPM": 50, "TPM": 800000 }, "Tier 4": { "IPM": 150, "TPM": 3000000 }, "Tier 5": { "IPM": 250, "TPM": 8000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-image-1-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1758845821, "openapi_enum": true }, "deprecation": [ { "announced": "2026-06-02", "shutdown_date": "2026-12-01", "replacement": "`gpt-image-2`", "phase": "upcoming", "section": "2026-06-02: GPT Image model deprecations", "source": "https://developers.openai.com/api/docs/deprecations#2026-06-02-gpt-image-model-deprecations" }, { "announced": null, "shutdown_date": "2026-12-01", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-12-01", "intro": "A cost-efficient version of GPT Image 1. It is a natively multimodal language model that accepts both text and image inputs, and produces image outputs.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-image-1-mini", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-06-02-gpt-image-model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-image-1.5", "record_kind": "model", "canonical_model": "gpt-image-1.5", "display_name": "GPT-Image-1.5", "description": "Our previous image generation model", "aliases": [], "snapshots": [ "gpt-image-1.5-2025-12-16" ], "default_snapshot": "gpt-image-1.5-2025-12-16", "family": "image", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-12-16", "release_date_source": "changelog", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "image", "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": true, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": true, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": true, "image_edit_api": true, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Batch", "route": "/v1/batch" }, { "name": "Image generation", "route": "/v1/images/generations" }, { "name": "Image edit", "route": "/v1/images/edits" } ], "tools": [], "features_documented": [ "inpainting" ], "pricing": { "standard": { "image_input": 8.0, "_unit": "per 1M tokens", "image_cached_input": 2.0, "image_output": 32.0, "text_input": 5.0, "text_cached_input": 1.25, "text_output": 10.0 }, "batch": { "image_input": 4.0, "_unit": "per 1M tokens", "image_cached_input": 1.0, "image_output": 16.0, "text_input": 2.5, "text_cached_input": 0.63, "text_output": 5.0 }, "model_page:Text tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Cached input": { "price": 1.25, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } }, "model_page:Image tokens": { "Input": { "price": 8.0, "unit": "1M tokens" }, "Cached input": { "price": 2.0, "unit": "1M tokens" }, "Output": { "price": 32.0, "unit": "1M tokens" } }, "model_page:Image generation": { "1024x1024": { "price": 0.133, "unit": "image" }, "1024x1536": { "price": 0.2, "unit": "image" }, "1536x1024": { "price": 0.2, "unit": "image" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "TPM", "IPM" ], "note": null, "tiers": { "Tier 1": { "TPM": 100000, "IPM": 5 }, "Tier 2": { "TPM": 250000, "IPM": 20 }, "Tier 3": { "TPM": 800000, "IPM": 50 }, "Tier 4": { "TPM": 3000000, "IPM": 150 }, "Tier 5": { "TPM": 8000000, "IPM": 250 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-image-1.5", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1764030620, "openapi_enum": true }, "deprecation": [ { "announced": "2026-06-02", "shutdown_date": "2026-12-01", "replacement": "`gpt-image-2`", "phase": "upcoming", "section": "2026-06-02: GPT Image model deprecations", "source": "https://developers.openai.com/api/docs/deprecations#2026-06-02-gpt-image-model-deprecations" }, { "announced": null, "shutdown_date": "2026-12-01", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-12-01", "intro": "GPT Image 1.5 is our previous image generation model, with better instruction following and adherence to prompts. Learn more in our [GPT Image 1.5 usage guide](/api/docs/guides/image-generation).", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-image-1.5", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-06-02-gpt-image-model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-image-1.5-2025-12-16", "record_kind": "snapshot", "canonical_model": "gpt-image-1.5", "display_name": "GPT-Image-1.5 (snapshot gpt-image-1.5-2025-12-16)", "description": "Our previous image generation model", "aliases": [], "snapshots": [], "default_snapshot": "gpt-image-1.5-2025-12-16", "family": "image", "status": [ "DOCUMENTED" ], "flags": [], "release_date": "2025-12-16", "release_date_source": "snapshot date in id", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "image", "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": true, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": true, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": true, "image_edit_api": true, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Batch", "route": "/v1/batch" }, { "name": "Image generation", "route": "/v1/images/generations" }, { "name": "Image edit", "route": "/v1/images/edits" } ], "tools": [], "features_documented": [ "inpainting" ], "pricing": { "standard": { "image_input": 8.0, "_unit": "per 1M tokens", "image_cached_input": 2.0, "image_output": 32.0, "text_input": 5.0, "text_cached_input": 1.25, "text_output": 10.0 }, "batch": { "image_input": 4.0, "_unit": "per 1M tokens", "image_cached_input": 1.0, "image_output": 16.0, "text_input": 2.5, "text_cached_input": 0.63, "text_output": 5.0 }, "model_page:Text tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Cached input": { "price": 1.25, "unit": "1M tokens" }, "Output": { "price": 10.0, "unit": "1M tokens" } }, "model_page:Image tokens": { "Input": { "price": 8.0, "unit": "1M tokens" }, "Cached input": { "price": 2.0, "unit": "1M tokens" }, "Output": { "price": 32.0, "unit": "1M tokens" } }, "model_page:Image generation": { "1024x1024": { "price": 0.133, "unit": "image" }, "1024x1536": { "price": 0.2, "unit": "image" }, "1536x1024": { "price": 0.2, "unit": "image" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "TPM", "IPM" ], "note": null, "tiers": { "Tier 1": { "TPM": 100000, "IPM": 5 }, "Tier 2": { "TPM": 250000, "IPM": 20 }, "Tier 3": { "TPM": 800000, "IPM": 50 }, "Tier 4": { "TPM": 3000000, "IPM": 150 }, "Tier 5": { "TPM": 8000000, "IPM": 250 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-image-1.5", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-image-1.5", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-image-2", "record_kind": "model", "canonical_model": "gpt-image-2", "display_name": "GPT-Image-2", "description": "State-of-the-art image generation model", "aliases": [], "snapshots": [ "gpt-image-2-2026-04-21" ], "default_snapshot": "gpt-image-2-2026-04-21", "family": "image", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-04-21", "release_date_source": "changelog", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "image" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": false, "image_in": true, "image_out": true, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": true, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": true, "image_edit_api": true, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Batch", "route": "/v1/batch" }, { "name": "Image generation", "route": "/v1/images/generations" }, { "name": "Image edit", "route": "/v1/images/edits" } ], "tools": [], "features_documented": [ "inpainting" ], "pricing": { "standard": { "image_input": 8.0, "_unit": "per 1M tokens", "image_cached_input": 2.0, "image_output": 30.0, "text_input": 5.0, "text_cached_input": 1.25 }, "batch": { "image_input": 4.0, "_unit": "per 1M tokens", "image_cached_input": 1.0, "image_output": 15.0, "text_input": 2.5, "text_cached_input": 0.625 } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "TPM", "IPM" ], "note": null, "tiers": { "Tier 1": { "TPM": 100000, "IPM": 5 }, "Tier 2": { "TPM": 250000, "IPM": 20 }, "Tier 3": { "TPM": 800000, "IPM": 50 }, "Tier 4": { "TPM": 3000000, "IPM": 150 }, "Tier 5": { "TPM": 8000000, "IPM": 250 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-image-2", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1776399795, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT Image 2 is our state-of-the-art image generation model for fast, high-quality image generation and editing. It supports flexible image sizes and high-fidelity image inputs. Learn more in our [image generation guide](/api/docs/guides/image-generation), or see the [pricing page](/api/docs/pricing#image-generation) and [image generation calculator](/api/docs/guides/image-generation#calculating-costs) for cost estimates.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-image-2", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-image-2-2026-04-21", "record_kind": "snapshot", "canonical_model": "gpt-image-2", "display_name": "GPT-Image-2 (snapshot gpt-image-2-2026-04-21)", "description": "State-of-the-art image generation model", "aliases": [], "snapshots": [], "default_snapshot": "gpt-image-2-2026-04-21", "family": "image", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-04-21", "release_date_source": "snapshot date in id", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "image" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": false, "image_in": true, "image_out": true, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": true, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": true, "image_edit_api": true, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Batch", "route": "/v1/batch" }, { "name": "Image generation", "route": "/v1/images/generations" }, { "name": "Image edit", "route": "/v1/images/edits" } ], "tools": [], "features_documented": [ "inpainting" ], "pricing": { "standard": { "image_input": 8.0, "_unit": "per 1M tokens", "image_cached_input": 2.0, "image_output": 30.0, "text_input": 5.0, "text_cached_input": 1.25 }, "batch": { "image_input": 4.0, "_unit": "per 1M tokens", "image_cached_input": 1.0, "image_output": 15.0, "text_input": 2.5, "text_cached_input": 0.625 } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "TPM", "IPM" ], "note": null, "tiers": { "Tier 1": { "TPM": 100000, "IPM": 5 }, "Tier 2": { "TPM": 250000, "IPM": 20 }, "Tier 3": { "TPM": 800000, "IPM": 50 }, "Tier 4": { "TPM": 3000000, "IPM": 150 }, "Tier 5": { "TPM": 8000000, "IPM": 250 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-image-2", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1776399994, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-image-2", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-image-2.5-flare", "record_kind": "model", "canonical_model": "gpt-image-2.5-flare", "display_name": "GPT-Image-2.5 Flare", "description": "Fast, high-quality everyday image generation", "aliases": [], "snapshots": [ "gpt-image-2.5-flare-2026-09-08" ], "default_snapshot": "gpt-image-2.5-flare-2026-09-08", "family": "image", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-09-08", "release_date_source": "changelog", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "image" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": false, "image_in": true, "image_out": true, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": true, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": true, "image_edit_api": true, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Image generation", "route": "/v1/images/generations" }, { "name": "Image edit", "route": "/v1/images/edits" } ], "tools": [], "features_documented": [ "inpainting" ], "pricing": { "standard": { "image_input": 8.0, "_unit": "per 1M tokens", "image_cached_input": 2.0, "image_output": 30.0, "text_input": 5.0, "text_cached_input": 1.25 }, "model_page:Text tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Cached input": { "price": 1.25, "unit": "1M tokens" } }, "model_page:Image tokens": { "Input": { "price": 8.0, "unit": "1M tokens" }, "Cached input": { "price": 2.0, "unit": "1M tokens" }, "Output": { "price": 30.0, "unit": "1M tokens" } }, "notes": [ "Image output costs $30 per million tokens. Text output is not billed because this model outputs images, not text.", "Token rates match GPT Image 2. The GPT Image 2 calculator does not estimate GPT Image 2.5 token consumption." ] }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "TPM", "IPM" ], "note": null, "tiers": { "Tier 1": { "TPM": 100000, "IPM": 5 }, "Tier 2": { "TPM": 250000, "IPM": 20 }, "Tier 3": { "TPM": 800000, "IPM": 50 }, "Tier 4": { "TPM": 3000000, "IPM": 150 }, "Tier 5": { "TPM": 8000000, "IPM": 250 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-image-2.5-flare", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1788563147, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT Image 2.5 Flare is our fastest model for high-quality, everyday image generation. It accepts text and image inputs and produces image outputs. It supports `low`, `medium`, `high`, `xhigh`, `max`, and `auto` quality settings. Select it directly in the Image API or as the model of the Responses API image generation tool. Learn more in the [image generation guide](/api/docs/guides/image-generation).", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models/gpt-image-2.5-flare -> 200", "get_model": { "status": 200, "id": "gpt-image-2.5-flare", "object": "model", "created": 1788563147, "owned_by": "system", "shutdown_date": null } }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-image-2.5-flare", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-image-2.5-flare-2026-09-08", "record_kind": "snapshot", "canonical_model": "gpt-image-2.5-flare", "display_name": "GPT-Image-2.5 Flare (snapshot gpt-image-2.5-flare-2026-09-08)", "description": "Fast, high-quality everyday image generation", "aliases": [], "snapshots": [], "default_snapshot": "gpt-image-2.5-flare-2026-09-08", "family": "image", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-09-08", "release_date_source": "snapshot date in id", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "image" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": false, "image_in": true, "image_out": true, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": true, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": true, "image_edit_api": true, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Image generation", "route": "/v1/images/generations" }, { "name": "Image edit", "route": "/v1/images/edits" } ], "tools": [], "features_documented": [ "inpainting" ], "pricing": { "standard": { "image_input": 8.0, "_unit": "per 1M tokens", "image_cached_input": 2.0, "image_output": 30.0, "text_input": 5.0, "text_cached_input": 1.25 }, "model_page:Text tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Cached input": { "price": 1.25, "unit": "1M tokens" } }, "model_page:Image tokens": { "Input": { "price": 8.0, "unit": "1M tokens" }, "Cached input": { "price": 2.0, "unit": "1M tokens" }, "Output": { "price": 30.0, "unit": "1M tokens" } }, "notes": [ "Image output costs $30 per million tokens. Text output is not billed because this model outputs images, not text.", "Token rates match GPT Image 2. The GPT Image 2 calculator does not estimate GPT Image 2.5 token consumption." ] }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "TPM", "IPM" ], "note": null, "tiers": { "Tier 1": { "TPM": 100000, "IPM": 5 }, "Tier 2": { "TPM": 250000, "IPM": 20 }, "Tier 3": { "TPM": 800000, "IPM": 50 }, "Tier 4": { "TPM": 3000000, "IPM": 150 }, "Tier 5": { "TPM": 8000000, "IPM": 250 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-image-2.5-flare", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1788851006, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-image-2.5-flare", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-image-2.5-sunburst", "record_kind": "model", "canonical_model": "gpt-image-2.5-sunburst", "display_name": "GPT-Image-2.5 Sunburst", "description": "Our most capable model for image generation and editing", "aliases": [], "snapshots": [ "gpt-image-2.5-sunburst-2026-09-08" ], "default_snapshot": "gpt-image-2.5-sunburst-2026-09-08", "family": "image", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-09-08", "release_date_source": "changelog", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "image" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": false, "image_in": true, "image_out": true, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": true, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": true, "image_edit_api": true, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Image generation", "route": "/v1/images/generations" }, { "name": "Image edit", "route": "/v1/images/edits" } ], "tools": [], "features_documented": [ "inpainting" ], "pricing": { "standard": { "image_input": 8.0, "_unit": "per 1M tokens", "image_cached_input": 2.0, "image_output": 30.0, "text_input": 5.0, "text_cached_input": 1.25 }, "model_page:Text tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Cached input": { "price": 1.25, "unit": "1M tokens" } }, "model_page:Image tokens": { "Input": { "price": 8.0, "unit": "1M tokens" }, "Cached input": { "price": 2.0, "unit": "1M tokens" }, "Output": { "price": 30.0, "unit": "1M tokens" } }, "notes": [ "Image output costs $30 per million tokens. Text output is not billed because this model outputs images, not text.", "Token rates match GPT Image 2. The GPT Image 2 calculator does not estimate GPT Image 2.5 token consumption." ] }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "TPM", "IPM" ], "note": null, "tiers": { "Tier 1": { "TPM": 100000, "IPM": 5 }, "Tier 2": { "TPM": 250000, "IPM": 20 }, "Tier 3": { "TPM": 800000, "IPM": 50 }, "Tier 4": { "TPM": 3000000, "IPM": 150 }, "Tier 5": { "TPM": 8000000, "IPM": 250 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1788563162, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT Image 2.5 Sunburst generates and edits images from text and image inputs. Use it for workflows where editing precision matters most. It supports `low`, `medium`, `high`, `xhigh`, `max`, and `auto` quality settings. Select it directly in the Image API or as the model of the Responses API image generation tool. Learn more in the [image generation guide](/api/docs/guides/image-generation).", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-image-2.5-sunburst-2026-09-08", "record_kind": "snapshot", "canonical_model": "gpt-image-2.5-sunburst", "display_name": "GPT-Image-2.5 Sunburst (snapshot gpt-image-2.5-sunburst-2026-09-08)", "description": "Our most capable model for image generation and editing", "aliases": [], "snapshots": [], "default_snapshot": "gpt-image-2.5-sunburst-2026-09-08", "family": "image", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-09-08", "release_date_source": "snapshot date in id", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "image" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": false, "image_in": true, "image_out": true, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": true, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": true, "image_edit_api": true, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Image generation", "route": "/v1/images/generations" }, { "name": "Image edit", "route": "/v1/images/edits" } ], "tools": [], "features_documented": [ "inpainting" ], "pricing": { "standard": { "image_input": 8.0, "_unit": "per 1M tokens", "image_cached_input": 2.0, "image_output": 30.0, "text_input": 5.0, "text_cached_input": 1.25 }, "model_page:Text tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Cached input": { "price": 1.25, "unit": "1M tokens" } }, "model_page:Image tokens": { "Input": { "price": 8.0, "unit": "1M tokens" }, "Cached input": { "price": 2.0, "unit": "1M tokens" }, "Output": { "price": 30.0, "unit": "1M tokens" } }, "notes": [ "Image output costs $30 per million tokens. Text output is not billed because this model outputs images, not text.", "Token rates match GPT Image 2. The GPT Image 2 calculator does not estimate GPT Image 2.5 token consumption." ] }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "TPM", "IPM" ], "note": null, "tiers": { "Tier 1": { "TPM": 100000, "IPM": 5 }, "Tier 2": { "TPM": 250000, "IPM": 20 }, "Tier 3": { "TPM": 800000, "IPM": 50 }, "Tier 4": { "TPM": 3000000, "IPM": 150 }, "Tier 5": { "TPM": 8000000, "IPM": 250 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1788851010, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-live-1", "record_kind": "model", "canonical_model": "gpt-live-1", "display_name": "GPT-Live 1", "description": "Our premier model for natural, expressive voice conversations with smooth interruption handling.", "aliases": [], "snapshots": [], "default_snapshot": "gpt-live-1", "family": "live", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-09-10", "release_date_source": "changelog", "knowledge_cutoff": "2025-07-31", "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ], "unsupported": [ "image", "video" ] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": true, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Live", "route": "/v1/live/sessions" } ], "tools": [], "features_documented": [ "function_calling", "streaming" ], "pricing": { "standard": { "session_duration": 0.05, "_unit": "per minute (billed per second)" }, "model_page:Live session duration": { "Per minute": { "price": 0.05, "unit": "minute" } }, "notes": [ "Voice sessions cost $0.05 per minute, billed per second. Backend model and tool usage is billed separately.", "Session duration is not rounded up to the next whole minute.", "Backend Responses calls use the normal pricing for the configured model and tools." ] }, "rate_limits": { "documented_tiers": { "Concurrent sessions": { "metrics": [ "Concurrent sessions" ], "note": null, "tiers": { "Tier 1": { "Concurrent sessions": 25 }, "Tier 2": { "Concurrent sessions": 50 }, "Tier 3": { "Concurrent sessions": 200 }, "Tier 4": { "Concurrent sessions": 300 }, "Tier 5": { "Concurrent sessions": 500 } } } }, "notes": [ "Rate limits are measured in concurrent sessions.", "Unsupported usage tiers: Free." ], "source": "https://developers.openai.com/api/docs/models/gpt-live-1", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1788889407, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-Live 1 is a full-duplex voice model for real-time conversations. It can listen and speak at the same time, and delegate reasoning and tool use to a backend agent. Learn how to [get started with GPT-Live](/api/docs/guides/live), [configure delegation](/api/docs/guides/live-delegation), and [prompt the model](/api/docs/guides/live-prompting).", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models/gpt-live-1 -> 200", "get_model": { "status": 200, "id": "gpt-live-1", "object": "model", "created": 1788889407, "owned_by": "system", "shutdown_date": null } }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-live-1", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-live-transcribe", "record_kind": "model", "canonical_model": "gpt-live-transcribe", "display_name": "GPT-Live-Transcribe", "description": "Low-latency speech-to-text model for realtime transcription", "aliases": [], "snapshots": [], "default_snapshot": "gpt-live-transcribe", "family": "speech-to-text", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-07-28", "release_date_source": "changelog", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": true, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Realtime transcription", "route": "/v1/realtime/transcription_sessions" } ], "tools": [], "features_documented": [ "streaming" ], "pricing": { "standard": { "audio_duration": 0.017, "_unit": "per minute" }, "model_page:Realtime audio duration": { "Price": { "price": 0.017, "unit": "minute" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 60000 }, "Tier 2": { "RPM": 2000, "TPM": 210000 }, "Tier 3": { "RPM": 5000, "TPM": 390000 }, "Tier 4": { "RPM": 10000, "TPM": 600000 }, "Tier 5": { "RPM": 10000, "TPM": 780000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-live-transcribe", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1785168034, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT Live Transcribe is a streaming speech-to-text model for applications that need low-latency transcript deltas from live audio. It supports tunable latency, unstructured context, keyword hints, and multiple language hints.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-live-transcribe", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-oss-120b", "record_kind": "model", "canonical_model": "gpt-oss-120b", "display_name": "gpt-oss-120b", "description": "Most powerful open-weight model, fits into an H100 GPU", "aliases": [], "snapshots": [], "default_snapshot": "gpt-oss-120b", "family": "open-weight", "status": [ "DOCUMENTED" ], "flags": [ "NOT_RESOLVABLE_WITH_OUR_KEY" ], "release_date": "2025-08-05", "release_date_source": "public OpenAI announcement (not in downloaded docs)", "knowledge_cutoff": "2024-06-01", "context_window": 131072, "max_input": null, "max_output": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "low", "medium", "high" ], "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": false, "tool_code_interpreter": true, "tool_image_generation": false, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "code_interpreter", "function_calling", "mcp", "web_search" ], "features_documented": [ "function_calling", "streaming", "structured_outputs" ], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 0, "TPM": 0, "Batch queue limit": 0 }, "Tier 2": { "RPM": 0, "TPM": 0, "Batch queue limit": 0 }, "Tier 3": { "RPM": 0, "TPM": 0, "Batch queue limit": 0 }, "Tier 4": { "RPM": 0, "TPM": 0, "Batch queue limit": 0 }, "Tier 5": { "RPM": 0, "TPM": 0, "Batch queue limit": 0 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-oss-120b", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false, "distribution": "open weights on Hugging Face (Apache 2.0); documented Responses/Batch endpoint table, rate limits 0 for all tiers" }, "deprecation": [], "shutdown_date": null, "intro": "`gpt-oss-120b`is our most powerful open-weight model, which fits into a single H100 GPU (117B parameters with 5.1B active parameters). [Download gpt-oss-120b on HuggingFace](https://huggingface.co/openai/gpt-oss-120b). **Key features** - **Permissive Apache 2.0 license:** Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment. - **Configurable reasoning effort:** Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs. - **Full chain-of-thought:** Gain complete access t", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "failure", "http_status": 404, "request_note": "GET /v1/models/gpt-oss-120b -> 404 (a 404 with our key never means the model does not exist)", "get_model": { "status": 404, "error_type": "invalid_request_error", "error_code": "model_not_found", "error_message": "The model 'gpt-oss-120b' does not exist" } }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-oss-120b", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-oss-20b", "record_kind": "model", "canonical_model": "gpt-oss-20b", "display_name": "gpt-oss-20b", "description": "Medium-sized open-weight model for low latency", "aliases": [], "snapshots": [], "default_snapshot": "gpt-oss-20b", "family": "open-weight", "status": [ "DOCUMENTED" ], "flags": [], "release_date": "2025-08-05", "release_date_source": "public OpenAI announcement (not in downloaded docs)", "knowledge_cutoff": "2024-06-01", "context_window": 131072, "max_input": null, "max_output": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": [ "low", "medium", "high" ], "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": false, "tool_code_interpreter": true, "tool_image_generation": false, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "code_interpreter", "function_calling", "mcp", "web_search" ], "features_documented": [ "function_calling", "streaming", "structured_outputs" ], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 0, "TPM": 0, "Batch queue limit": 0 }, "Tier 2": { "RPM": 0, "TPM": 0, "Batch queue limit": 0 }, "Tier 3": { "RPM": 0, "TPM": 0, "Batch queue limit": 0 }, "Tier 4": { "RPM": 0, "TPM": 0, "Batch queue limit": 0 }, "Tier 5": { "RPM": 0, "TPM": 0, "Batch queue limit": 0 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-oss-20b", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false, "distribution": "open weights on Hugging Face (Apache 2.0); documented Responses/Batch endpoint table, rate limits 0 for all tiers" }, "deprecation": [], "shutdown_date": null, "intro": "`gpt-oss-20b` is our medium-sized open-weight model for low latency, local, or specialized use-cases (21B parameters with 3.6B active parameters). [Download gpt-oss-20b on HuggingFace](https://huggingface.co/openai/gpt-oss-20b). **Key features** - **Permissive Apache 2.0 license:** Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment. - **Configurable reasoning effort:** Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs. - **Full chain-of-thought:** Gain complet", "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-oss-20b", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-realtime", "record_kind": "model", "canonical_model": "gpt-realtime", "display_name": "GPT-Realtime", "description": "Model capable of realtime text and audio inputs and outputs", "aliases": [], "snapshots": [ "gpt-realtime-2025-08-28" ], "default_snapshot": "gpt-realtime-2025-08-28", "family": "realtime", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-08-28", "release_date_source": "changelog", "knowledge_cutoff": "2023-10-01", "context_window": 32000, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text", "audio", "image" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": true, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Realtime", "route": "/v1/realtime" } ], "tools": [], "features_documented": [ "function_calling", "prompt_caching" ], "pricing": { "standard": { "audio_input": 32.0, "_unit": "per 1M tokens", "audio_cached_input": 0.4, "audio_output": 64.0, "text_input": 4.0, "text_cached_input": 0.4, "text_output": 16.0, "image_input": 5.0, "image_cached_input": 0.5 }, "model_page:Text tokens": { "Input": { "price": 4.0, "unit": "1M tokens" }, "Cached input": { "price": 0.4, "unit": "1M tokens" }, "Output": { "price": 16.0, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 32.0, "unit": "1M tokens" }, "Cached input": { "price": 0.4, "unit": "1M tokens" }, "Output": { "price": 64.0, "unit": "1M tokens" } }, "model_page:Image tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Cached input": { "price": 0.5, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 200, "RPD": 1000, "TPM": 40000 }, "Tier 2": { "RPM": 400, "RPD": null, "TPM": 200000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 800000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 4000000 }, "Tier 5": { "RPM": 20000, "RPD": null, "TPM": 15000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-realtime", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1756271701, "openapi_enum": true }, "deprecation": [ { "announced": "2026-07-20", "shutdown_date": "2027-01-20", "replacement": "`gpt-realtime-2.1`", "phase": "upcoming", "section": "2026-07-20: Legacy audio, realtime, and transcription models", "source": "https://developers.openai.com/api/docs/deprecations#2026-07-20-legacy-audio-realtime-and-transcription-models" }, { "announced": null, "shutdown_date": "2027-01-20", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2027-01-20", "intro": "This is our first general-availability realtime model, capable of responding to audio and text inputs in realtime over WebRTC, WebSocket, or SIP connections.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-realtime", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-07-20-legacy-audio-realtime-and-transcription-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-realtime-1.5", "record_kind": "model", "canonical_model": "gpt-realtime-1.5", "display_name": "GPT-Realtime-1.5", "description": "The best voice model for audio in, audio out", "aliases": [], "snapshots": [], "default_snapshot": "gpt-realtime-1.5", "family": "realtime", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-02-23", "release_date_source": "changelog", "knowledge_cutoff": "2024-09-30", "context_window": 32000, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text", "audio", "image" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": true, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Realtime", "route": "/v1/realtime" } ], "tools": [], "features_documented": [ "function_calling", "prompt_caching" ], "pricing": { "standard": { "audio_input": 32.0, "_unit": "per 1M tokens", "audio_cached_input": 0.4, "audio_output": 64.0, "text_input": 4.0, "text_cached_input": 0.4, "text_output": 16.0, "image_input": 5.0, "image_cached_input": 0.5 }, "model_page:Text tokens": { "Input": { "price": 4.0, "unit": "1M tokens" }, "Cached input": { "price": 0.4, "unit": "1M tokens" }, "Output": { "price": 16.0, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 32.0, "unit": "1M tokens" }, "Cached input": { "price": 0.4, "unit": "1M tokens" }, "Output": { "price": 64.0, "unit": "1M tokens" } }, "model_page:Image tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Cached input": { "price": 0.5, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 200, "RPD": 1000, "TPM": 40000 }, "Tier 2": { "RPM": 400, "RPD": null, "TPM": 200000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 800000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 4000000 }, "Tier 5": { "RPM": 20000, "RPD": null, "TPM": 15000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-realtime-1.5", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1771461469, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-Realtime-1.5 is our flagship audio model for voice agents and customer support.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-realtime-1.5", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-realtime-2", "record_kind": "model", "canonical_model": "gpt-realtime-2", "display_name": "GPT-Realtime-2", "description": "Reasoning model with tool use", "aliases": [], "snapshots": [], "default_snapshot": "gpt-realtime-2", "family": "realtime", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-05-07", "release_date_source": "changelog", "knowledge_cutoff": "2024-09-30", "context_window": 128000, "max_input": null, "max_output": 32000, "modalities": { "input": [ "text", "audio", "image" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": true, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Realtime", "route": "/v1/realtime" } ], "tools": [], "features_documented": [ "function_calling", "prompt_caching" ], "pricing": { "standard": { "audio_input": 32.0, "_unit": "per 1M tokens", "audio_cached_input": 0.4, "audio_output": 64.0, "text_input": 4.0, "text_cached_input": 0.4, "text_output": 24.0, "image_input": 5.0, "image_cached_input": 0.5 }, "model_page:Text tokens": { "Input": { "price": 4.0, "unit": "1M tokens" }, "Cached input": { "price": 0.4, "unit": "1M tokens" }, "Output": { "price": 24.0, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 32.0, "unit": "1M tokens" }, "Cached input": { "price": 0.4, "unit": "1M tokens" }, "Output": { "price": 64.0, "unit": "1M tokens" } }, "model_page:Image tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Cached input": { "price": 0.5, "unit": "1M tokens" } }, "notes": [ "GPT-Realtime-2 supports configurable reasoning effort. Higher reasoning effort can increase latency and output token usage." ] }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 200, "RPD": 1000, "TPM": 40000 }, "Tier 2": { "RPM": 400, "RPD": null, "TPM": 200000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 800000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 4000000 }, "Tier 5": { "RPM": 20000, "RPD": null, "TPM": 15000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-realtime-2", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1778006032, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-Realtime-2 is our most capable realtime voice model. It supports speech-to-speech interactions with configurable reasoning effort, stronger instruction following, and more reliable tool use for complex voice-agent workflows.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-realtime-2", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-realtime-2.1", "record_kind": "model", "canonical_model": "gpt-realtime-2.1", "display_name": "GPT-Realtime-2.1", "description": "Reasoning model with tool use", "aliases": [], "snapshots": [], "default_snapshot": "gpt-realtime-2.1", "family": "realtime", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-07-06", "release_date_source": "changelog", "knowledge_cutoff": "2024-09-30", "context_window": 128000, "max_input": null, "max_output": 32000, "modalities": { "input": [ "text", "audio", "image" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": true, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Realtime", "route": "/v1/realtime" } ], "tools": [], "features_documented": [ "function_calling", "prompt_caching" ], "pricing": { "standard": { "audio_input": 32.0, "_unit": "per 1M tokens", "audio_cached_input": 0.4, "audio_output": 64.0, "text_input": 4.0, "text_cached_input": 0.4, "text_output": 24.0, "image_input": 5.0, "image_cached_input": 0.5 }, "model_page:Text tokens": { "Input": { "price": 4.0, "unit": "1M tokens" }, "Cached input": { "price": 0.4, "unit": "1M tokens" }, "Output": { "price": 24.0, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 32.0, "unit": "1M tokens" }, "Cached input": { "price": 0.4, "unit": "1M tokens" }, "Output": { "price": 64.0, "unit": "1M tokens" } }, "model_page:Image tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Cached input": { "price": 0.5, "unit": "1M tokens" } }, "notes": [ "GPT-Realtime-2.1 supports configurable reasoning effort. Higher reasoning effort can increase latency and output token usage." ] }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 200, "RPD": 1000, "TPM": 40000 }, "Tier 2": { "RPM": 400, "RPD": null, "TPM": 200000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 800000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 4000000 }, "Tier 5": { "RPM": 20000, "RPD": null, "TPM": 15000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-realtime-2.1", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1782254687, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-Realtime-2.1 updates GPT-Realtime-2 with improved alphanumeric recognition, silence and noise handling, and interruption behavior. It supports speech-to-speech interactions with configurable reasoning effort, instruction following, and tool use for complex voice-agent workflows.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-realtime-2.1", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-realtime-2.1-mini", "record_kind": "model", "canonical_model": "gpt-realtime-2.1-mini", "display_name": "GPT-Realtime-2.1 Mini", "description": "Reasoning model with tool use", "aliases": [], "snapshots": [], "default_snapshot": "gpt-realtime-2.1-mini", "family": "realtime", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-07-06", "release_date_source": "changelog", "knowledge_cutoff": "2024-09-30", "context_window": 128000, "max_input": null, "max_output": 32000, "modalities": { "input": [ "text", "audio", "image" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": true, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Realtime", "route": "/v1/realtime" } ], "tools": [], "features_documented": [ "function_calling", "prompt_caching" ], "pricing": { "standard": { "audio_input": 10.0, "_unit": "per 1M tokens", "audio_cached_input": 0.3, "audio_output": 20.0, "text_input": 0.6, "text_cached_input": 0.06, "text_output": 2.4, "image_input": 0.8, "image_cached_input": 0.08 }, "model_page:Text tokens": { "Input": { "price": 0.6, "unit": "1M tokens" }, "Cached input": { "price": 0.06, "unit": "1M tokens" }, "Output": { "price": 2.4, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 10.0, "unit": "1M tokens" }, "Cached input": { "price": 0.3, "unit": "1M tokens" }, "Output": { "price": 20.0, "unit": "1M tokens" } }, "model_page:Image tokens": { "Input": { "price": 0.8, "unit": "1M tokens" }, "Cached input": { "price": 0.08, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 200, "TPM": 40000 }, "Tier 2": { "RPM": 400, "TPM": 200000 }, "Tier 3": { "RPM": 5000, "TPM": 800000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000 }, "Tier 5": { "RPM": 20000, "TPM": 15000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-realtime-2.1-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1782254706, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-Realtime-2.1 Mini is a distilled reasoning model for faster, lower-cost realtime voice interactions. It supports audio and text inputs over WebRTC, WebSocket, or SIP connections and improves alphanumeric recognition over GPT-Realtime-2.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-realtime-2.1-mini", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-realtime-2025-08-28", "record_kind": "snapshot", "canonical_model": "gpt-realtime", "display_name": "GPT-Realtime (snapshot gpt-realtime-2025-08-28)", "description": "Model capable of realtime text and audio inputs and outputs", "aliases": [], "snapshots": [], "default_snapshot": "gpt-realtime-2025-08-28", "family": "realtime", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-08-28", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 32000, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text", "audio", "image" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": true, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Realtime", "route": "/v1/realtime" } ], "tools": [], "features_documented": [ "function_calling", "prompt_caching" ], "pricing": { "standard": { "audio_input": 32.0, "_unit": "per 1M tokens", "audio_cached_input": 0.4, "audio_output": 64.0, "text_input": 4.0, "text_cached_input": 0.4, "text_output": 16.0, "image_input": 5.0, "image_cached_input": 0.5 }, "model_page:Text tokens": { "Input": { "price": 4.0, "unit": "1M tokens" }, "Cached input": { "price": 0.4, "unit": "1M tokens" }, "Output": { "price": 16.0, "unit": "1M tokens" } }, "model_page:Audio tokens": { "Input": { "price": 32.0, "unit": "1M tokens" }, "Cached input": { "price": 0.4, "unit": "1M tokens" }, "Output": { "price": 64.0, "unit": "1M tokens" } }, "model_page:Image tokens": { "Input": { "price": 5.0, "unit": "1M tokens" }, "Cached input": { "price": 0.5, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 200, "RPD": 1000, "TPM": 40000 }, "Tier 2": { "RPM": 400, "RPD": null, "TPM": 200000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 800000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 4000000 }, "Tier 5": { "RPM": 20000, "RPD": null, "TPM": 15000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-realtime", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1756271773, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-realtime", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-realtime-mini", "record_kind": "model", "canonical_model": "gpt-realtime-mini", "display_name": "GPT-Realtime Mini", "description": "A cost-efficient version of GPT-Realtime", "aliases": [], "snapshots": [ "gpt-realtime-mini-2025-10-06", "gpt-realtime-mini-2025-12-15" ], "default_snapshot": "gpt-realtime-mini-2025-12-15", "family": "realtime", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-10-06", "release_date_source": "changelog", "knowledge_cutoff": "2023-10-01", "context_window": 32000, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": true, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Realtime", "route": "/v1/realtime" } ], "tools": [], "features_documented": [ "function_calling", "prompt_caching" ], "pricing": { "standard": { "audio_input": 10.0, "_unit": "per 1M tokens", "audio_cached_input": 0.3, "audio_output": 20.0, "text_input": 0.6, "text_cached_input": 0.06, "text_output": 2.4, "image_input": 0.8, "image_cached_input": 0.08 }, "model_page:Text tokens": { "Input": { "price": 0.6, "unit": "1M tokens" }, "Cached input": { "price": 0.06, "unit": "1M tokens" }, "Output": { "price": 2.4, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 200, "TPM": 40000 }, "Tier 2": { "RPM": 400, "TPM": 200000 }, "Tier 3": { "RPM": 5000, "TPM": 800000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000 }, "Tier 5": { "RPM": 20000, "TPM": 15000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-realtime-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1759517133, "openapi_enum": true }, "deprecation": [ { "announced": "2026-07-20", "shutdown_date": "2027-01-20", "replacement": "`gpt-realtime-2.1-mini`", "phase": "upcoming", "section": "2026-07-20: Legacy audio, realtime, and transcription models", "source": "https://developers.openai.com/api/docs/deprecations#2026-07-20-legacy-audio-realtime-and-transcription-models" }, { "announced": null, "shutdown_date": "2027-01-20", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2027-01-20", "intro": "GPT-Realtime Mini is capable of responding to audio and text inputs in realtime over WebRTC, WebSocket, or SIP connections.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-realtime-mini", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-07-20-legacy-audio-realtime-and-transcription-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-realtime-mini-2025-10-06", "record_kind": "snapshot", "canonical_model": "gpt-realtime-mini", "display_name": "GPT-Realtime Mini (snapshot gpt-realtime-mini-2025-10-06)", "description": "A cost-efficient version of GPT-Realtime", "aliases": [], "snapshots": [], "default_snapshot": "gpt-realtime-mini-2025-12-15", "family": "realtime", "status": [ "DOCUMENTED", "RETIRED" ], "flags": [], "release_date": "2025-10-06", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 32000, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": true, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Realtime", "route": "/v1/realtime" } ], "tools": [], "features_documented": [ "function_calling", "prompt_caching" ], "pricing": { "standard": { "audio_input": 10.0, "_unit": "per 1M tokens", "audio_cached_input": 0.3, "audio_output": 20.0, "text_input": 0.6, "text_cached_input": 0.06, "text_output": 2.4, "image_input": 0.8, "image_cached_input": 0.08 }, "model_page:Text tokens": { "Input": { "price": 0.6, "unit": "1M tokens" }, "Cached input": { "price": 0.06, "unit": "1M tokens" }, "Output": { "price": 2.4, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 200, "TPM": 40000 }, "Tier 2": { "RPM": 400, "TPM": 200000 }, "Tier 3": { "RPM": 5000, "TPM": 800000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000 }, "Tier 5": { "RPM": 20000, "TPM": 15000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-realtime-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-07-23", "replacement": "`gpt-realtime-2.1-mini`", "phase": "past", "section": "2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown" } ], "shutdown_date": "2026-07-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-realtime-mini", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-realtime-mini-2025-12-15", "record_kind": "snapshot", "canonical_model": "gpt-realtime-mini", "display_name": "GPT-Realtime Mini (snapshot gpt-realtime-mini-2025-12-15)", "description": "A cost-efficient version of GPT-Realtime", "aliases": [], "snapshots": [], "default_snapshot": "gpt-realtime-mini-2025-12-15", "family": "realtime", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-12-15", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 32000, "max_input": null, "max_output": 4096, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": true, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Realtime", "route": "/v1/realtime" } ], "tools": [], "features_documented": [ "function_calling", "prompt_caching" ], "pricing": { "standard": { "audio_input": 10.0, "_unit": "per 1M tokens", "audio_cached_input": 0.3, "audio_output": 20.0, "text_input": 0.6, "text_cached_input": 0.06, "text_output": 2.4, "image_input": 0.8, "image_cached_input": 0.08 }, "model_page:Text tokens": { "Input": { "price": 0.6, "unit": "1M tokens" }, "Cached input": { "price": 0.06, "unit": "1M tokens" }, "Output": { "price": 2.4, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 200, "TPM": 40000 }, "Tier 2": { "RPM": 400, "TPM": 200000 }, "Tier 3": { "RPM": 5000, "TPM": 800000 }, "Tier 4": { "RPM": 10000, "TPM": 4000000 }, "Tier 5": { "RPM": 20000, "TPM": 15000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-realtime-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1765612007, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-realtime-mini", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-realtime-translate", "record_kind": "model", "canonical_model": "gpt-realtime-translate", "display_name": "GPT-Realtime-Translate", "description": "Streaming speech-to-speech translation model", "aliases": [], "snapshots": [], "default_snapshot": "gpt-realtime-translate", "family": "speech-to-text", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-05-07", "release_date_source": "changelog", "knowledge_cutoff": "2024-09-30", "context_window": 16000, "max_input": null, "max_output": 2000, "modalities": { "input": [ "audio" ], "output": [ "audio", "text" ], "unsupported": [] }, "capabilities": { "text_in": false, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": true, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Realtime translation", "route": "/v1/realtime/translations" } ], "tools": [], "features_documented": [ "streaming" ], "pricing": { "standard": { "audio_duration": 0.034, "_unit": "per minute" }, "model_page:Realtime audio duration": { "Price": { "price": 0.034, "unit": "minute" } }, "notes": [ "GPT-Realtime-Translate is priced by audio duration rather than text tokens." ] }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "Minutes-of-audio per minute" ], "note": null, "tiers": { "Tier 1": { "Minutes-of-audio per minute": 50 }, "Tier 2": { "Minutes-of-audio per minute": 200 }, "Tier 3": { "Minutes-of-audio per minute": 400 }, "Tier 4": { "Minutes-of-audio per minute": 650 }, "Tier 5": { "Minutes-of-audio per minute": 850 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-realtime-translate", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1777950216, "openapi_enum": false }, "deprecation": [], "shutdown_date": null, "intro": "GPT-Realtime-Translate is a streaming speech-to-speech translation model for live multilingual audio experiences. It uses a dedicated realtime translation endpoint and returns translated audio plus transcript deltas while source audio is still arriving. GPT-Realtime-Translate is priced by audio duration rather than text tokens.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-realtime-translate", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-realtime-whisper", "record_kind": "model", "canonical_model": "gpt-realtime-whisper", "display_name": "GPT-Realtime-Whisper", "description": "Streaming speech-to-text model for realtime transcription", "aliases": [], "snapshots": [], "default_snapshot": "gpt-realtime-whisper", "family": "speech-to-text", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-05-07", "release_date_source": "changelog", "knowledge_cutoff": "2024-09-30", "context_window": 16000, "max_input": null, "max_output": 2000, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": true, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Realtime transcription", "route": "/v1/realtime/transcription_sessions" } ], "tools": [], "features_documented": [ "streaming" ], "pricing": { "standard": { "audio_duration": 0.017, "_unit": "per minute" }, "model_page:Realtime audio duration": { "Price": { "price": 0.017, "unit": "minute" } }, "notes": [ "GPT-Realtime-Whisper is priced by audio duration rather than text tokens." ] }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "Minutes-of-audio per minute" ], "note": null, "tiers": { "Tier 1": { "Minutes-of-audio per minute": 100 }, "Tier 2": { "Minutes-of-audio per minute": 350 }, "Tier 3": { "Minutes-of-audio per minute": 650 }, "Tier 4": { "Minutes-of-audio per minute": 1000 }, "Tier 5": { "Minutes-of-audio per minute": 1300 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-realtime-whisper", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1778012060, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT-Realtime-Whisper is a streaming speech-to-text model for applications that need low-latency transcript deltas from live audio. It is designed for realtime use cases where developers need to tune latency and accuracy. GPT-Realtime-Whisper is priced by audio duration rather than text tokens.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-realtime-whisper", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-rosalind-research", "record_kind": "id_only", "canonical_model": "gpt-rosalind-research", "display_name": "gpt-rosalind-research", "description": "Life sciences reasoning for approved organizations (trusted-access program).", "aliases": [], "snapshots": [], "default_snapshot": null, "family": "life-sciences", "status": [ "DOCUMENTED", "ACCOUNT_RESTRICTED" ], "flags": [ "NO_MODEL_PAGE" ], "release_date": "2026-09-08", "release_date_source": "changelog", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "standard": { "input": 5.0, "_unit": "per 1M tokens", "cached_input": 0.5, "output": 25.0 } }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": "Trusted-access program for approved life-sciences research (billing starts 2026-10-05)", "availability": { "account": "Trusted-access program for approved life-sciences research (billing starts 2026-10-05)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "restricted", "http_status": 404, "request_note": "GET /v1/models/gpt-rosalind-research -> 404 model_not_found", "get_model": { "status": 404, "error_type": "invalid_request_error", "error_code": "model_not_found", "error_message": "The model 'gpt-rosalind-research' does not exist" } }, "sources": [ { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "gpt-transcribe", "record_kind": "model", "canonical_model": "gpt-transcribe", "display_name": "GPT-Transcribe", "description": "High-accuracy speech-to-text model for file and Realtime input transcription", "aliases": [], "snapshots": [], "default_snapshot": "gpt-transcribe", "family": "speech-to-text", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2026-07-28", "release_date_source": "changelog", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": true, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Realtime transcription", "route": "/v1/realtime/transcription_sessions" }, { "name": "Transcription", "route": "/v1/audio/transcriptions" } ], "tools": [], "features_documented": [ "streaming" ], "pricing": { "standard": { "audio_duration": 0.0045, "_unit": "per minute" }, "model_page:Transcription audio duration": { "Price": { "price": 0.0045, "unit": "minute" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 200000 }, "Tier 2": { "RPM": 5000, "TPM": 2000000 }, "Tier 3": { "RPM": 5000, "TPM": 4000000 }, "Tier 4": { "RPM": 10000, "TPM": 10000000 }, "Tier 5": { "RPM": 30000, "TPM": 150000000 } } } }, "source": "https://developers.openai.com/api/docs/models/gpt-transcribe", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1785168027, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "GPT Transcribe is a speech-to-text model for completed audio files, streamed file transcripts, and committed turns in Realtime sessions over WebSocket. It supports unstructured context, keyword hints, and multiple language hints to improve transcription of domain terms, multilingual audio, and code-switching.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/gpt-transcribe", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "o1", "record_kind": "model", "canonical_model": "o1", "display_name": "o1", "description": "Previous full o-series reasoning model", "aliases": [], "snapshots": [ "o1-2024-12-17" ], "default_snapshot": "o1-2024-12-17", "family": "o-series", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2024-12-17", "release_date_source": "changelog", "knowledge_cutoff": "2023-10-01", "context_window": 200000, "max_input": null, "max_output": 100000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": true, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "file_search", "function_calling", "mcp" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "streaming", "structured_outputs" ], "pricing": { "standard": { "input": 15.0, "_unit": "per 1M tokens", "cached_input": 7.5, "output": 60.0 }, "batch": { "input": 7.5, "_unit": "per 1M tokens", "output": 30.0 }, "model_page:Text tokens": { "Input": { "price": 15.0, "unit": "1M tokens" }, "Cached input": { "price": 7.5, "unit": "1M tokens" }, "Output": { "price": 60.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/o1", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1734375816, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-sol`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" }, { "announced": null, "shutdown_date": "2026-10-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-10-23", "intro": "The o1 series of models are trained with reinforcement learning to perform complex reasoning. o1 models think before they answer, producing a long internal chain of thought before responding to the user.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/o1", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "o1-2024-12-17", "record_kind": "snapshot", "canonical_model": "o1", "display_name": "o1 (snapshot o1-2024-12-17)", "description": "Previous full o-series reasoning model", "aliases": [], "snapshots": [], "default_snapshot": "o1-2024-12-17", "family": "o-series", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2024-12-17", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 200000, "max_input": null, "max_output": 100000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": true, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "file_search", "function_calling", "mcp" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "image_input", "streaming", "structured_outputs" ], "pricing": { "standard": { "input": 15.0, "_unit": "per 1M tokens", "cached_input": 7.5, "output": 60.0 }, "batch": { "input": 7.5, "_unit": "per 1M tokens", "output": 30.0 }, "model_page:Text tokens": { "Input": { "price": 15.0, "unit": "1M tokens" }, "Cached input": { "price": 7.5, "unit": "1M tokens" }, "Output": { "price": 60.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/o1", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1734326976, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-sol`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" }, { "announced": null, "shutdown_date": "2026-10-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-10-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/o1", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "o1-mini", "record_kind": "model", "canonical_model": "o1-mini", "display_name": "o1-mini", "description": "A small model alternative to o1", "aliases": [], "snapshots": [ "o1-mini-2024-09-12" ], "default_snapshot": "o1-mini-2024-09-12", "family": "o-series", "status": [ "DOCUMENTED", "RETIRED" ], "flags": [], "release_date": "2024-09-12", "release_date_source": "changelog", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 65536, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": false, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Assistants", "route": "/v1/assistants" } ], "tools": [ "code_interpreter", "file_search", "mcp" ], "features_documented": [ "file_search", "file_uploads", "streaming" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 1.1, "unit": "1M tokens" }, "Cached input": { "price": 0.55, "unit": "1M tokens" }, "Output": { "price": 4.4, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 200000, "Batch queue limit": null }, "Tier 2": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": null }, "Tier 3": { "RPM": 5000, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "TPM": 150000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/o1-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2025-04-28", "shutdown_date": "2025-10-27", "replacement": "`o4-mini`", "phase": "past", "section": "2025-04-28: `o1-preview` and `o1-mini`", "source": "https://developers.openai.com/api/docs/deprecations#2025-04-28-o1-preview-and-o1-mini" } ], "shutdown_date": "2025-10-27", "intro": "The o1 reasoning model is designed to solve hard problems across domains. o1-mini is a faster and more affordable reasoning model, but we recommend using the newer o3-mini model that features higher intelligence at the same latency and price as o1-mini.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "failure", "http_status": 404, "request_note": "GET /v1/models/o1-mini -> 404 (a 404 with our key never means the model does not exist)", "get_model": { "status": 404, "error_type": "invalid_request_error", "error_code": "model_not_found", "error_message": "The model 'o1-mini' does not exist" } }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/o1-mini", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-04-28-o1-preview-and-o1-mini", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "o1-mini-2024-09-12", "record_kind": "snapshot", "canonical_model": "o1-mini", "display_name": "o1-mini (snapshot o1-mini-2024-09-12)", "description": "A small model alternative to o1", "aliases": [], "snapshots": [], "default_snapshot": "o1-mini-2024-09-12", "family": "o-series", "status": [ "DOCUMENTED" ], "flags": [], "release_date": "2024-09-12", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 65536, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": false, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Assistants", "route": "/v1/assistants" } ], "tools": [ "code_interpreter", "file_search", "mcp" ], "features_documented": [ "file_search", "file_uploads", "streaming" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 1.1, "unit": "1M tokens" }, "Cached input": { "price": 0.55, "unit": "1M tokens" }, "Output": { "price": 4.4, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 200000, "Batch queue limit": null }, "Tier 2": { "RPM": 5000, "TPM": 2000000, "Batch queue limit": null }, "Tier 3": { "RPM": 5000, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "TPM": 150000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/o1-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/o1-mini", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "o1-preview", "record_kind": "model", "canonical_model": "o1-preview", "display_name": "o1 Preview", "description": "Preview of our first o-series reasoning model", "aliases": [], "snapshots": [ "o1-preview-2024-09-12" ], "default_snapshot": "o1-preview-2024-09-12", "family": "o-series", "status": [ "DOCUMENTED", "RETIRED", "PREVIEW" ], "flags": [], "release_date": "2024-09-12", "release_date_source": "changelog", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 32768, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Assistants", "route": "/v1/assistants" } ], "tools": [], "features_documented": [ "file_search", "file_uploads", "function_calling", "streaming", "structured_outputs" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 15.0, "unit": "1M tokens" }, "Cached input": { "price": 7.5, "unit": "1M tokens" }, "Output": { "price": 60.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": null }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": null }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/o1-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2025-04-28", "shutdown_date": "2025-07-28", "replacement": "`o3`", "phase": "past", "section": "2025-04-28: `o1-preview` and `o1-mini`", "source": "https://developers.openai.com/api/docs/deprecations#2025-04-28-o1-preview-and-o1-mini" } ], "shutdown_date": "2025-07-28", "intro": "Research preview of the o1 series of models, trained with reinforcement learning to perform complex reasoning. o1 models think before they answer, producing a long internal chain of thought before responding to the user.", "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/o1-preview", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-04-28-o1-preview-and-o1-mini", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "o1-preview-2024-09-12", "record_kind": "snapshot", "canonical_model": "o1-preview", "display_name": "o1 Preview (snapshot o1-preview-2024-09-12)", "description": "Preview of our first o-series reasoning model", "aliases": [], "snapshots": [], "default_snapshot": "o1-preview-2024-09-12", "family": "o-series", "status": [ "DOCUMENTED", "PREVIEW" ], "flags": [], "release_date": "2024-09-12", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 128000, "max_input": null, "max_output": 32768, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Assistants", "route": "/v1/assistants" } ], "tools": [], "features_documented": [ "file_search", "file_uploads", "function_calling", "streaming", "structured_outputs" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 15.0, "unit": "1M tokens" }, "Cached input": { "price": 7.5, "unit": "1M tokens" }, "Output": { "price": 60.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": null }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": null }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/o1-preview", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/o1-preview", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "o1-pro", "record_kind": "model", "canonical_model": "o1-pro", "display_name": "o1-pro", "description": "Version of o1 with more compute for better responses", "aliases": [], "snapshots": [ "o1-pro-2025-03-19" ], "default_snapshot": "o1-pro-2025-03-19", "family": "o-series", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-03-19", "release_date_source": "changelog", "knowledge_cutoff": "2023-10-01", "context_window": 200000, "max_input": null, "max_output": 100000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": true, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "file_search", "function_calling", "mcp" ], "features_documented": [ "function_calling", "image_input", "structured_outputs" ], "pricing": { "standard": { "input": 150.0, "_unit": "per 1M tokens", "output": 600.0 }, "batch": { "input": 75.0, "_unit": "per 1M tokens", "output": 300.0 }, "model_page:Text tokens": { "Input": { "price": 150.0, "unit": "1M tokens" }, "Output": { "price": 600.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/o1-pro", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1742251791, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-sol` (`reasoning.mode: pro`)", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" }, { "announced": null, "shutdown_date": "2026-10-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-10-23", "intro": "The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide consistently better answers. o1-pro is available in the [Responses API only](/api/docs/api-reference/responses) to enable support for multi-turn model interactions before responding to API requests, and other advanced API features in the future.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/o1-pro", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "o1-pro-2025-03-19", "record_kind": "snapshot", "canonical_model": "o1-pro", "display_name": "o1-pro (snapshot o1-pro-2025-03-19)", "description": "Version of o1 with more compute for better responses", "aliases": [], "snapshots": [], "default_snapshot": "o1-pro-2025-03-19", "family": "o-series", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-03-19", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 200000, "max_input": null, "max_output": 100000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": true, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "file_search", "function_calling", "mcp" ], "features_documented": [ "function_calling", "image_input", "structured_outputs" ], "pricing": { "standard": { "input": 150.0, "_unit": "per 1M tokens", "output": 600.0 }, "batch": { "input": 75.0, "_unit": "per 1M tokens", "output": 300.0 }, "model_page:Text tokens": { "Input": { "price": 150.0, "unit": "1M tokens" }, "Output": { "price": 600.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/o1-pro", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1742251504, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-sol` (`reasoning.mode: pro`)", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" }, { "announced": null, "shutdown_date": "2026-10-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-10-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/o1-pro", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "o3", "record_kind": "model", "canonical_model": "o3", "display_name": "o3", "description": "Reasoning model for complex tasks, succeeded by GPT-5", "aliases": [], "snapshots": [ "o3-2025-04-16" ], "default_snapshot": "o3-2025-04-16", "family": "o-series", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-04-16", "release_date_source": "changelog", "knowledge_cutoff": "2024-06-01", "context_window": 200000, "max_input": null, "max_output": 100000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": true, "stored_completions": true, "distillation": true, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "evals", "file_search", "file_uploads", "function_calling", "image_input", "prompt_caching", "stored_completions", "streaming", "structured_outputs" ], "pricing": { "standard": { "input": 2.0, "_unit": "per 1M tokens", "cached_input": 0.5, "output": 8.0 }, "batch": { "input": 1.0, "_unit": "per 1M tokens", "output": 4.0 }, "flex": { "input": 1.0, "_unit": "per 1M tokens", "cached_input": 0.25, "output": 4.0 }, "fast": { "input": 3.5, "_unit": "per 1M tokens", "cached_input": 0.875, "output": 14.0 }, "model_page:Text tokens": { "Input": { "price": 1.0, "unit": "1M tokens" }, "Cached input": { "price": 0.25, "unit": "1M tokens" }, "Output": { "price": 4.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/o3", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1744225308, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images. o3 is succeeded by [GPT-5](/api/docs/models/gpt-5). Learn more about how to use our reasoning models in our [reasoning](/api/docs/guides/reasoning?api-mode=responses) guide.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/o3", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "o3-2025-04-16", "record_kind": "snapshot", "canonical_model": "o3", "display_name": "o3 (snapshot o3-2025-04-16)", "description": "Reasoning model for complex tasks, succeeded by GPT-5", "aliases": [], "snapshots": [], "default_snapshot": "o3-2025-04-16", "family": "o-series", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-04-16", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2024-06-01", "context_window": 200000, "max_input": null, "max_output": 100000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": true, "stored_completions": true, "distillation": true, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "evals", "file_search", "file_uploads", "function_calling", "image_input", "prompt_caching", "stored_completions", "streaming", "structured_outputs" ], "pricing": { "standard": { "input": 2.0, "_unit": "per 1M tokens", "cached_input": 0.5, "output": 8.0 }, "batch": { "input": 1.0, "_unit": "per 1M tokens", "output": 4.0 }, "flex": { "input": 1.0, "_unit": "per 1M tokens", "cached_input": 0.25, "output": 4.0 }, "fast": { "input": 3.5, "_unit": "per 1M tokens", "cached_input": 0.875, "output": 14.0 }, "model_page:Text tokens": { "Input": { "price": 1.0, "unit": "1M tokens" }, "Cached input": { "price": 0.25, "unit": "1M tokens" }, "Output": { "price": 4.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/o3", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1744133301, "openapi_enum": true }, "deprecation": [ { "announced": "2026-06-11", "shutdown_date": "2026-12-11", "replacement": "`gpt-5.6-sol`", "phase": "upcoming", "section": "2026-06-11: GPT-5 and o3 model deprecations", "source": "https://developers.openai.com/api/docs/deprecations#2026-06-11-gpt-5-and-o3-model-deprecations" }, { "announced": null, "shutdown_date": "2026-12-11", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-12-11", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/o3", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-06-11-gpt-5-and-o3-model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "o3-deep-research", "record_kind": "model", "canonical_model": "o3-deep-research", "display_name": "o3-deep-research", "description": "Our most powerful deep research model", "aliases": [], "snapshots": [ "o3-deep-research-2025-06-26" ], "default_snapshot": "o3-deep-research-2025-06-26", "family": "search", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "RETIRED" ], "flags": [ "STILL_LISTED_AFTER_DOCUMENTED_SHUTDOWN" ], "release_date": "2025-06-26", "release_date_source": "changelog", "knowledge_cutoff": "2024-06-01", "context_window": 200000, "max_input": null, "max_output": 100000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": false, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": true, "stored_completions": true, "distillation": true, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": false, "tool_code_interpreter": true, "tool_image_generation": false, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "code_interpreter", "mcp", "web_search" ], "features_documented": [ "evals", "file_uploads", "image_input", "prompt_caching", "stored_completions", "streaming" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 10.0, "unit": "1M tokens" }, "Cached input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 40.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 200000, "Batch queue limit": 200000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 300000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 500000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 2000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 10000000 } } } }, "source": "https://developers.openai.com/api/docs/models/o3-deep-research", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1749840121, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-07-23", "replacement": "`gpt-5.6-sol`", "phase": "past", "section": "2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown" }, { "announced": null, "shutdown_date": "2026-07-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-07-23", "intro": "o3-deep-research is our most advanced model for deep research, designed to tackle complex, multi-step research tasks. It can search and synthesize information from across the internet as well as from your own data—brought in through MCP connectors. Learn more about getting started with this model in our [deep research](/api/docs/guides/deep-research) guide.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models/o3-deep-research -> 200", "get_model": { "status": 200, "id": "o3-deep-research", "object": "model", "created": 1749840121, "owned_by": "system", "shutdown_date": "2026-07-23" } }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/o3-deep-research", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "o3-deep-research-2025-06-26", "record_kind": "snapshot", "canonical_model": "o3-deep-research", "display_name": "o3-deep-research (snapshot o3-deep-research-2025-06-26)", "description": "Our most powerful deep research model", "aliases": [], "snapshots": [], "default_snapshot": "o3-deep-research-2025-06-26", "family": "search", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "RETIRED" ], "flags": [ "STILL_LISTED_AFTER_DOCUMENTED_SHUTDOWN" ], "release_date": "2025-06-26", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2024-06-01", "context_window": 200000, "max_input": null, "max_output": 100000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": false, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": true, "stored_completions": true, "distillation": true, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": false, "tool_code_interpreter": true, "tool_image_generation": false, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "code_interpreter", "mcp", "web_search" ], "features_documented": [ "evals", "file_uploads", "image_input", "prompt_caching", "stored_completions", "streaming" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 10.0, "unit": "1M tokens" }, "Cached input": { "price": 2.5, "unit": "1M tokens" }, "Output": { "price": 40.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 200000, "Batch queue limit": 200000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 300000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 500000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 2000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 10000000 } } } }, "source": "https://developers.openai.com/api/docs/models/o3-deep-research", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1750865219, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-07-23", "replacement": "`gpt-5.6-sol`", "phase": "past", "section": "2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown" }, { "announced": null, "shutdown_date": "2026-07-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-07-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/o3-deep-research", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "o3-mini", "record_kind": "model", "canonical_model": "o3-mini", "display_name": "o3-mini", "description": "A small model alternative to o3", "aliases": [], "snapshots": [ "o3-mini-2025-01-31" ], "default_snapshot": "o3-mini-2025-01-31", "family": "o-series", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-01-31", "release_date_source": "changelog", "knowledge_cutoff": "2023-10-01", "context_window": 200000, "max_input": null, "max_output": 100000, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "streaming", "structured_outputs" ], "pricing": { "standard": { "input": 1.1, "_unit": "per 1M tokens", "cached_input": 0.55, "output": 4.4 }, "batch": { "input": 0.55, "_unit": "per 1M tokens", "output": 2.2 }, "model_page:Text tokens": { "Input": { "price": 1.1, "unit": "1M tokens" }, "Cached input": { "price": 0.55, "unit": "1M tokens" }, "Output": { "price": 4.4, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 1000, "TPM": 100000, "Batch queue limit": 1000000 }, "Tier 2": { "RPM": 2000, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 3": { "RPM": 5000, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "TPM": 150000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/o3-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1737146383, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-sol`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" }, { "announced": null, "shutdown_date": "2026-10-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-10-23", "intro": "o3-mini is our newest small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini supports key developer features, like Structured Outputs, function calling, and Batch API.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/o3-mini", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "o3-mini-2025-01-31", "record_kind": "snapshot", "canonical_model": "o3-mini", "display_name": "o3-mini (snapshot o3-mini-2025-01-31)", "description": "A small model alternative to o3", "aliases": [], "snapshots": [], "default_snapshot": "o3-mini-2025-01-31", "family": "o-series", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-01-31", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2023-10-01", "context_window": 200000, "max_input": null, "max_output": 100000, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Assistants", "route": "/v1/assistants" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "image_generation", "mcp" ], "features_documented": [ "file_search", "file_uploads", "function_calling", "streaming", "structured_outputs" ], "pricing": { "standard": { "input": 1.1, "_unit": "per 1M tokens", "cached_input": 0.55, "output": 4.4 }, "batch": { "input": 0.55, "_unit": "per 1M tokens", "output": 2.2 }, "model_page:Text tokens": { "Input": { "price": 1.1, "unit": "1M tokens" }, "Cached input": { "price": 0.55, "unit": "1M tokens" }, "Output": { "price": 4.4, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 1000, "TPM": 100000, "Batch queue limit": 1000000 }, "Tier 2": { "RPM": 2000, "TPM": 200000, "Batch queue limit": 2000000 }, "Tier 3": { "RPM": 5000, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "TPM": 150000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/o3-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1738010200, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-sol`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" }, { "announced": null, "shutdown_date": "2026-10-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-10-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/o3-mini", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "o3-pro", "record_kind": "model", "canonical_model": "o3-pro", "display_name": "o3-pro", "description": "Version of o3 with more compute for better responses", "aliases": [], "snapshots": [ "o3-pro-2025-06-10" ], "default_snapshot": "o3-pro-2025-06-10", "family": "o-series", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2025-06-10", "release_date_source": "changelog", "knowledge_cutoff": "2024-06-01", "context_window": 200000, "max_input": null, "max_output": 100000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": false, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "function_calling", "image_input", "structured_outputs" ], "pricing": { "standard": { "input": 20.0, "_unit": "per 1M tokens", "output": 80.0 }, "batch": { "input": 10.0, "_unit": "per 1M tokens", "output": 40.0 }, "model_page:Text tokens": { "Input": { "price": 20.0, "unit": "1M tokens" }, "Output": { "price": 80.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/o3-pro", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1748475349, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently better answers. o3-pro is available in the [Responses API only](/api/docs/api-reference/responses) to enable support for multi-turn model interactions before responding to API requests, and other advanced API features in the future. Since o3-pro is designed to tackle tough problems, some requests may take several minutes to finish. To avoid timeouts, try using [background mode](/api/docs/guides/back", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/o3-pro", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "o3-pro-2025-06-10", "record_kind": "snapshot", "canonical_model": "o3-pro", "display_name": "o3-pro (snapshot o3-pro-2025-06-10)", "description": "Version of o3 with more compute for better responses", "aliases": [], "snapshots": [], "default_snapshot": "o3-pro-2025-06-10", "family": "o-series", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-06-10", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2024-06-01", "context_window": 200000, "max_input": null, "max_output": 100000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": true, "function_calling": true, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": false, "tool_image_generation": true, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "file_search", "function_calling", "image_generation", "mcp", "web_search" ], "features_documented": [ "function_calling", "image_input", "structured_outputs" ], "pricing": { "standard": { "input": 20.0, "_unit": "per 1M tokens", "output": 80.0 }, "batch": { "input": 10.0, "_unit": "per 1M tokens", "output": 40.0 }, "model_page:Text tokens": { "Input": { "price": 20.0, "unit": "1M tokens" }, "Output": { "price": 80.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 500, "TPM": 30000, "Batch queue limit": 90000 }, "Tier 2": { "RPM": 5000, "TPM": 450000, "Batch queue limit": 1350000 }, "Tier 3": { "RPM": 5000, "TPM": 800000, "Batch queue limit": 50000000 }, "Tier 4": { "RPM": 10000, "TPM": 2000000, "Batch queue limit": 200000000 }, "Tier 5": { "RPM": 10000, "TPM": 30000000, "Batch queue limit": 5000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/o3-pro", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1749166761, "openapi_enum": true }, "deprecation": [ { "announced": "2026-06-11", "shutdown_date": "2026-12-11", "replacement": "`gpt-5.6-sol` (`reasoning.mode: pro`)", "phase": "upcoming", "section": "2026-06-11: GPT-5 and o3 model deprecations", "source": "https://developers.openai.com/api/docs/deprecations#2026-06-11-gpt-5-and-o3-model-deprecations" }, { "announced": null, "shutdown_date": "2026-12-11", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-12-11", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/o3-pro", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-06-11-gpt-5-and-o3-model-deprecations", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "o4-mini", "record_kind": "model", "canonical_model": "o4-mini", "display_name": "o4-mini", "description": "Fast, cost-efficient reasoning model, succeeded by GPT-5 Mini", "aliases": [], "snapshots": [ "o4-mini-2025-04-16" ], "default_snapshot": "o4-mini-2025-04-16", "family": "o-series", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-04-16", "release_date_source": "changelog", "knowledge_cutoff": "2024-06-01", "context_window": 200000, "max_input": null, "max_output": 100000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": true, "stored_completions": true, "distillation": true, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": false, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "mcp", "web_search" ], "features_documented": [ "evals", "file_search", "file_uploads", "fine_tuning", "function_calling", "image_input", "prompt_caching", "stored_completions", "streaming", "structured_outputs" ], "pricing": { "standard": { "input": 1.1, "_unit": "per 1M tokens", "cached_input": 0.275, "output": 4.4 }, "batch": { "input": 0.55, "_unit": "per 1M tokens", "output": 2.2 }, "flex": { "input": 0.55, "_unit": "per 1M tokens", "cached_input": 0.138, "output": 2.2 }, "fast": { "input": 2.0, "_unit": "per 1M tokens", "cached_input": 0.5, "output": 8.0 }, "model_page:Text tokens": { "Input": { "price": 1.1, "unit": "1M tokens" }, "Cached input": { "price": 0.275, "unit": "1M tokens" }, "Output": { "price": 4.4, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 1000, "TPM": 100000, "Batch queue limit": 1000000 }, "Tier 2": { "RPM": 2000, "TPM": 2000000, "Batch queue limit": 2000000 }, "Tier 3": { "RPM": 5000, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "TPM": 150000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/o4-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1744225351, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-terra`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" }, { "announced": null, "shutdown_date": "2026-10-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-10-23", "intro": "o4-mini is our latest small o-series model. It's optimized for fast, effective reasoning with exceptionally efficient performance in coding and visual tasks. It's succeeded by [GPT-5 Mini](/api/docs/models/gpt-5-mini). Learn more about how to use our reasoning models in our [reasoning](/api/docs/guides/reasoning?api-mode=responses) guide.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/o4-mini", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "o4-mini-2025-04-16", "record_kind": "snapshot", "canonical_model": "o4-mini", "display_name": "o4-mini (snapshot o4-mini-2025-04-16)", "description": "Fast, cost-efficient reasoning model, succeeded by GPT-5 Mini", "aliases": [], "snapshots": [], "default_snapshot": "o4-mini-2025-04-16", "family": "o-series", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-04-16", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2024-06-01", "context_window": 200000, "max_input": null, "max_output": 100000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": true, "function_calling": true, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": true, "stored_completions": true, "distillation": true, "inpainting": false, "fine_tuning": true, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": true, "tool_code_interpreter": true, "tool_image_generation": false, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": true, "web_search_feature": false }, "endpoints": [ { "name": "Chat Completions", "route": "/v1/chat/completions" }, { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" }, { "name": "Fine-tuning", "route": "/v1/fine-tuning" } ], "tools": [ "code_interpreter", "file_search", "function_calling", "mcp", "web_search" ], "features_documented": [ "evals", "file_search", "file_uploads", "fine_tuning", "function_calling", "image_input", "prompt_caching", "stored_completions", "streaming", "structured_outputs" ], "pricing": { "standard": { "input": 1.1, "_unit": "per 1M tokens", "cached_input": 0.275, "output": 4.4 }, "batch": { "input": 0.55, "_unit": "per 1M tokens", "output": 2.2 }, "flex": { "input": 0.55, "_unit": "per 1M tokens", "cached_input": 0.138, "output": 2.2 }, "fast": { "input": 2.0, "_unit": "per 1M tokens", "cached_input": 0.5, "output": 8.0 }, "model_page:Text tokens": { "Input": { "price": 1.1, "unit": "1M tokens" }, "Cached input": { "price": 0.275, "unit": "1M tokens" }, "Output": { "price": 4.4, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 1000, "TPM": 100000, "Batch queue limit": 1000000 }, "Tier 2": { "RPM": 2000, "TPM": 2000000, "Batch queue limit": 2000000 }, "Tier 3": { "RPM": 5000, "TPM": 4000000, "Batch queue limit": 40000000 }, "Tier 4": { "RPM": 10000, "TPM": 10000000, "Batch queue limit": 1000000000 }, "Tier 5": { "RPM": 30000, "TPM": 150000000, "Batch queue limit": 15000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/o4-mini", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": true, "fast": true }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1744133506, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-10-23", "replacement": "`gpt-5.6-terra`", "phase": "upcoming", "section": "2026-04-22: Legacy GPT model snapshots", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots" }, { "announced": null, "shutdown_date": "2026-10-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-10-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/o4-mini", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "o4-mini-deep-research", "record_kind": "model", "canonical_model": "o4-mini-deep-research", "display_name": "o4-mini-deep-research", "description": "Faster, more affordable deep research model", "aliases": [], "snapshots": [ "o4-mini-deep-research-2025-06-26" ], "default_snapshot": "o4-mini-deep-research-2025-06-26", "family": "search", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "RETIRED" ], "flags": [ "STILL_LISTED_AFTER_DOCUMENTED_SHUTDOWN" ], "release_date": "2025-06-26", "release_date_source": "changelog", "knowledge_cutoff": "2024-06-01", "context_window": 200000, "max_input": null, "max_output": 100000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": false, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": true, "stored_completions": true, "distillation": true, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": false, "tool_code_interpreter": true, "tool_image_generation": false, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "code_interpreter", "mcp", "web_search" ], "features_documented": [ "evals", "file_uploads", "image_input", "prompt_caching", "stored_completions", "streaming" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 2.0, "unit": "1M tokens" }, "Cached input": { "price": 0.5, "unit": "1M tokens" }, "Output": { "price": 8.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 1000, "TPM": 200000, "Batch queue limit": 200000 }, "Tier 2": { "RPM": 2000, "TPM": 2000000, "Batch queue limit": 300000 }, "Tier 3": { "RPM": 5000, "TPM": 4000000, "Batch queue limit": 500000 }, "Tier 4": { "RPM": 10000, "TPM": 10000000, "Batch queue limit": 2000000 }, "Tier 5": { "RPM": 30000, "TPM": 150000000, "Batch queue limit": 10000000 } } } }, "source": "https://developers.openai.com/api/docs/models/o4-mini-deep-research", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1749685485, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-07-23", "replacement": "`gpt-5.6-sol`", "phase": "past", "section": "2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown" }, { "announced": null, "shutdown_date": "2026-07-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-07-23", "intro": "o4-mini-deep-research is our faster, more affordable deep research model—ideal for tackling complex, multi-step research tasks. It can search and synthesize information from across the internet as well as from your own data, brought in through MCP connectors. Learn more about how to use this model in our [deep research](/api/docs/guides/deep-research) guide.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/o4-mini-deep-research", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "o4-mini-deep-research-2025-06-26", "record_kind": "snapshot", "canonical_model": "o4-mini-deep-research", "display_name": "o4-mini-deep-research (snapshot o4-mini-deep-research-2025-06-26)", "description": "Faster, more affordable deep research model", "aliases": [], "snapshots": [], "default_snapshot": "o4-mini-deep-research-2025-06-26", "family": "search", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "RETIRED" ], "flags": [ "STILL_LISTED_AFTER_DOCUMENTED_SHUTDOWN" ], "release_date": "2025-06-26", "release_date_source": "snapshot date in id", "knowledge_cutoff": "2024-06-01", "context_window": 200000, "max_input": null, "max_output": 100000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": true, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": true, "structured_outputs": false, "function_calling": false, "prompt_caching": true, "extended_prompt_cache_retention_24h": "unknown", "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": true, "evals": true, "stored_completions": true, "distillation": true, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": true, "tool_file_search": false, "tool_code_interpreter": true, "tool_image_generation": false, "tool_mcp": true, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Responses", "route": "/v1/responses" }, { "name": "Batch", "route": "/v1/batch" } ], "tools": [ "code_interpreter", "mcp", "web_search" ], "features_documented": [ "evals", "file_uploads", "image_input", "prompt_caching", "stored_completions", "streaming" ], "pricing": { "model_page:Text tokens": { "Input": { "price": 2.0, "unit": "1M tokens" }, "Cached input": { "price": 0.5, "unit": "1M tokens" }, "Output": { "price": 8.0, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "TPM", "Batch queue limit" ], "note": null, "tiers": { "Tier 1": { "RPM": 1000, "TPM": 200000, "Batch queue limit": 200000 }, "Tier 2": { "RPM": 2000, "TPM": 2000000, "Batch queue limit": 300000 }, "Tier 3": { "RPM": 5000, "TPM": 4000000, "Batch queue limit": 500000 }, "Tier 4": { "RPM": 10000, "TPM": 10000000, "Batch queue limit": 2000000 }, "Tier 5": { "RPM": 30000, "TPM": 150000000, "Batch queue limit": 10000000 } } } }, "source": "https://developers.openai.com/api/docs/models/o4-mini-deep-research", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1750866121, "openapi_enum": true }, "deprecation": [ { "announced": "2026-04-22", "shutdown_date": "2026-07-23", "replacement": "`gpt-5.6-sol`", "phase": "past", "section": "2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)", "source": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown" }, { "announced": null, "shutdown_date": "2026-07-23", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-07-23", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/o4-mini-deep-research", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots-july-2026-shutdown", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "omni-moderation-2024-09-26", "record_kind": "snapshot", "canonical_model": "omni-moderation-latest", "display_name": "omni-moderation (snapshot omni-moderation-2024-09-26)", "description": "Identify potentially harmful content in text and images", "aliases": [], "snapshots": [], "default_snapshot": "omni-moderation-2024-09-26", "family": "moderation", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2024-09-26", "release_date_source": "snapshot date in id", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": true, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Batch", "route": "/v1/batch" }, { "name": "Moderation", "route": "/v1/moderations" } ], "tools": [], "features_documented": [ "image_input" ], "pricing": { "standard": { "input": 0.0, "_unit": "per 1M tokens" } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM" ], "note": null, "tiers": { "free": { "RPM": 250, "RPD": 5000, "TPM": 10000 }, "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 10000 }, "Tier 2": { "RPM": 500, "RPD": null, "TPM": 20000 }, "Tier 3": { "RPM": 1000, "RPD": null, "TPM": 50000 }, "Tier 4": { "RPM": 2000, "RPD": null, "TPM": 250000 }, "Tier 5": { "RPM": 5000, "RPD": null, "TPM": 500000 } } } }, "source": "https://developers.openai.com/api/docs/models/omni-moderation-latest", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1732734466, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/omni-moderation-latest", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "omni-moderation-latest", "record_kind": "model", "canonical_model": "omni-moderation-latest", "display_name": "omni-moderation", "description": "Identify potentially harmful content in text and images", "aliases": [], "snapshots": [ "omni-moderation-2024-09-26" ], "default_snapshot": "omni-moderation-2024-09-26", "family": "moderation", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2024-09-26", "release_date_source": "changelog", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": true, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": false, "structured_outputs": false, "function_calling": false, "prompt_caching": false, "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": false, "file_uploads": false, "evals": false, "stored_completions": false, "distillation": false, "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": true, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": false, "web_search_feature": false }, "endpoints": [ { "name": "Batch", "route": "/v1/batch" }, { "name": "Moderation", "route": "/v1/moderations" } ], "tools": [], "features_documented": [ "image_input" ], "pricing": { "standard": { "input": 0.0, "_unit": "per 1M tokens" } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM" ], "note": null, "tiers": { "free": { "RPM": 250, "RPD": 5000, "TPM": 10000 }, "Tier 1": { "RPM": 500, "RPD": 10000, "TPM": 10000 }, "Tier 2": { "RPM": 500, "RPD": null, "TPM": 20000 }, "Tier 3": { "RPM": 1000, "RPD": null, "TPM": 50000 }, "Tier 4": { "RPM": 2000, "RPD": null, "TPM": 250000 }, "Tier 5": { "RPM": 5000, "RPD": null, "TPM": 500000 } } } }, "source": "https://developers.openai.com/api/docs/models/omni-moderation-latest", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1731689265, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "Moderation models are free models designed to detect harmful content. This model is our most capable moderation model, accepting images as input as well. You can find the model card [here](https://cdn.openai.com/API/docs/omni_moderation_information_for_developers.pdf).", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/omni-moderation-latest", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "sora-2", "record_kind": "model", "canonical_model": "sora-2", "display_name": "Sora 2", "description": "Flagship video generation with synced audio", "aliases": [], "snapshots": [ "sora-2-2025-12-08", "sora-2-2025-10-06" ], "default_snapshot": "sora-2-2025-12-08", "family": "video", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-10-06", "release_date_source": "changelog", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "video", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": false, "image_in": true, "image_out": false, "audio_in": false, "audio_out": true, "video_in": false, "video_out": true, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": true, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Videos", "route": "/v1/videos" } ], "tools": [], "features_documented": [], "pricing": { "standard": { "video_output_720p": 0.1, "_unit": "per second" }, "batch": { "video_output_720p": 0.05, "_unit": "per second" }, "model_page:Video generation": {} }, "rate_limits": { "documented_tiers": { "Standard RPM": { "metrics": [ "RPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 25 }, "Tier 2": { "RPM": 50 }, "Tier 3": { "RPM": 125 }, "Tier 4": { "RPM": 200 }, "Tier 5": { "RPM": 375 } } } }, "source": "https://developers.openai.com/api/docs/models/sora-2", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1759708615, "openapi_enum": true }, "deprecation": [ { "announced": "2026-03-24", "shutdown_date": "2026-09-24", "replacement": "---", "phase": "upcoming", "section": "2026-03-24: Sora 2 video generation models and Videos API", "source": "https://developers.openai.com/api/docs/deprecations#2026-03-24-sora-2-video-generation-models-and-videos-api" }, { "announced": null, "shutdown_date": "2026-09-24", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-09-24", "intro": "Sora 2 is our new powerful media generation model, generating videos with synced audio. It can create richly detailed, dynamic clips from natural language or images.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/sora-2", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-03-24-sora-2-video-generation-models-and-videos-api", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "sora-2-2025-10-06", "record_kind": "snapshot", "canonical_model": "sora-2", "display_name": "Sora 2 (snapshot sora-2-2025-10-06)", "description": "Flagship video generation with synced audio", "aliases": [], "snapshots": [], "default_snapshot": "sora-2-2025-12-08", "family": "video", "status": [ "DOCUMENTED", "DEPRECATED" ], "flags": [], "release_date": "2025-10-06", "release_date_source": "snapshot date in id", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "video", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": false, "image_in": true, "image_out": false, "audio_in": false, "audio_out": true, "video_in": false, "video_out": true, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": true, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Videos", "route": "/v1/videos" } ], "tools": [], "features_documented": [], "pricing": { "standard": { "video_output_720p": 0.1, "_unit": "per second" }, "batch": { "video_output_720p": 0.05, "_unit": "per second" }, "model_page:Video generation": {} }, "rate_limits": { "documented_tiers": { "Standard RPM": { "metrics": [ "RPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 25 }, "Tier 2": { "RPM": 50 }, "Tier 3": { "RPM": 125 }, "Tier 4": { "RPM": 200 }, "Tier 5": { "RPM": 375 } } } }, "source": "https://developers.openai.com/api/docs/models/sora-2", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2026-03-24", "shutdown_date": "2026-09-24", "replacement": "---", "phase": "upcoming", "section": "2026-03-24: Sora 2 video generation models and Videos API", "source": "https://developers.openai.com/api/docs/deprecations#2026-03-24-sora-2-video-generation-models-and-videos-api" } ], "shutdown_date": "2026-09-24", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/sora-2", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-03-24-sora-2-video-generation-models-and-videos-api", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "sora-2-2025-12-08", "record_kind": "snapshot", "canonical_model": "sora-2", "display_name": "Sora 2 (snapshot sora-2-2025-12-08)", "description": "Flagship video generation with synced audio", "aliases": [], "snapshots": [], "default_snapshot": "sora-2-2025-12-08", "family": "video", "status": [ "DOCUMENTED", "DEPRECATED" ], "flags": [], "release_date": "2025-12-08", "release_date_source": "snapshot date in id", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "video", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": false, "image_in": true, "image_out": false, "audio_in": false, "audio_out": true, "video_in": false, "video_out": true, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": true, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Videos", "route": "/v1/videos" } ], "tools": [], "features_documented": [], "pricing": { "standard": { "video_output_720p": 0.1, "_unit": "per second" }, "batch": { "video_output_720p": 0.05, "_unit": "per second" }, "model_page:Video generation": {} }, "rate_limits": { "documented_tiers": { "Standard RPM": { "metrics": [ "RPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 25 }, "Tier 2": { "RPM": 50 }, "Tier 3": { "RPM": 125 }, "Tier 4": { "RPM": 200 }, "Tier 5": { "RPM": 375 } } } }, "source": "https://developers.openai.com/api/docs/models/sora-2", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2026-03-24", "shutdown_date": "2026-09-24", "replacement": "---", "phase": "upcoming", "section": "2026-03-24: Sora 2 video generation models and Videos API", "source": "https://developers.openai.com/api/docs/deprecations#2026-03-24-sora-2-video-generation-models-and-videos-api" } ], "shutdown_date": "2026-09-24", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/sora-2", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-03-24-sora-2-video-generation-models-and-videos-api", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "sora-2-pro", "record_kind": "model", "canonical_model": "sora-2-pro", "display_name": "Sora 2 Pro", "description": "Most advanced synced-audio video generation", "aliases": [], "snapshots": [ "sora-2-pro-2025-10-06" ], "default_snapshot": "sora-2-pro-2025-10-06", "family": "video", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED" ], "flags": [], "release_date": "2025-10-06", "release_date_source": "changelog", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "video", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": false, "image_in": true, "image_out": false, "audio_in": false, "audio_out": true, "video_in": false, "video_out": true, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": true, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Videos", "route": "/v1/videos" } ], "tools": [], "features_documented": [], "pricing": { "standard": { "video_output_720p": 0.3, "_unit": "per second", "video_output_1024p": 0.5, "video_output_1080p": 0.7 }, "batch": { "video_output_720p": 0.15, "_unit": "per second", "video_output_1024p": 0.25, "video_output_1080p": 0.35 }, "model_page:Video generation": {} }, "rate_limits": { "documented_tiers": { "Standard RPM": { "metrics": [ "RPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 10 }, "Tier 2": { "RPM": 25 }, "Tier 3": { "RPM": 50 }, "Tier 4": { "RPM": 75 }, "Tier 5": { "RPM": 150 } } } }, "source": "https://developers.openai.com/api/docs/models/sora-2-pro", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1759708663, "openapi_enum": true }, "deprecation": [ { "announced": "2026-03-24", "shutdown_date": "2026-09-24", "replacement": "---", "phase": "upcoming", "section": "2026-03-24: Sora 2 video generation models and Videos API", "source": "https://developers.openai.com/api/docs/deprecations#2026-03-24-sora-2-video-generation-models-and-videos-api" }, { "announced": null, "shutdown_date": "2026-09-24", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2026-09-24", "intro": "Sora 2 Pro is our state-of-the-art, most advanced media generation model, generating videos with synced audio. It can create richly detailed, dynamic clips from natural language or images.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/sora-2-pro", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-03-24-sora-2-video-generation-models-and-videos-api", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "sora-2-pro-2025-10-06", "record_kind": "snapshot", "canonical_model": "sora-2-pro", "display_name": "Sora 2 Pro (snapshot sora-2-pro-2025-10-06)", "description": "Most advanced synced-audio video generation", "aliases": [], "snapshots": [], "default_snapshot": "sora-2-pro-2025-10-06", "family": "video", "status": [ "DOCUMENTED", "DEPRECATED" ], "flags": [], "release_date": "2025-10-06", "release_date_source": "snapshot date in id", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "video", "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": false, "image_in": true, "image_out": false, "audio_in": false, "audio_out": true, "video_in": false, "video_out": true, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": true, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Videos", "route": "/v1/videos" } ], "tools": [], "features_documented": [], "pricing": { "standard": { "video_output_720p": 0.3, "_unit": "per second", "video_output_1024p": 0.5, "video_output_1080p": 0.7 }, "batch": { "video_output_720p": 0.15, "_unit": "per second", "video_output_1024p": 0.25, "video_output_1080p": 0.35 }, "model_page:Video generation": {} }, "rate_limits": { "documented_tiers": { "Standard RPM": { "metrics": [ "RPM" ], "note": null, "tiers": { "Tier 1": { "RPM": 10 }, "Tier 2": { "RPM": 25 }, "Tier 3": { "RPM": 50 }, "Tier 4": { "RPM": 75 }, "Tier 5": { "RPM": 150 } } } }, "source": "https://developers.openai.com/api/docs/models/sora-2-pro", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2026-03-24", "shutdown_date": "2026-09-24", "replacement": "---", "phase": "upcoming", "section": "2026-03-24: Sora 2 video generation models and Videos API", "source": "https://developers.openai.com/api/docs/deprecations#2026-03-24-sora-2-video-generation-models-and-videos-api" } ], "shutdown_date": "2026-09-24", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/sora-2-pro", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-03-24-sora-2-video-generation-models-and-videos-api", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-ada-001", "record_kind": "id_only", "canonical_model": "text-ada-001", "display_name": "text-ada-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "legacy-retired", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`gpt-3.5-turbo-instruct`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-babbage-001", "record_kind": "id_only", "canonical_model": "text-babbage-001", "display_name": "text-babbage-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "legacy-retired", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`gpt-3.5-turbo-instruct`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-curie-001", "record_kind": "id_only", "canonical_model": "text-curie-001", "display_name": "text-curie-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "legacy-retired", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`gpt-3.5-turbo-instruct`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-davinci-001", "record_kind": "id_only", "canonical_model": "text-davinci-001", "display_name": "text-davinci-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "legacy-retired", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`gpt-3.5-turbo-instruct`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-davinci-002", "record_kind": "id_only", "canonical_model": "text-davinci-002", "display_name": "text-davinci-002", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "legacy-retired", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`gpt-3.5-turbo-instruct`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-davinci-003", "record_kind": "id_only", "canonical_model": "text-davinci-003", "display_name": "text-davinci-003", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "legacy-retired", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`gpt-3.5-turbo-instruct`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-davinci-edit-001", "record_kind": "id_only", "canonical_model": "text-davinci-edit-001", "display_name": "text-davinci-edit-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "legacy-retired", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`gpt-4o`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-embedding-3-large", "record_kind": "model", "canonical_model": "text-embedding-3-large", "display_name": "text-embedding-3-large", "description": "Most capable embedding model", "aliases": [], "snapshots": [], "default_snapshot": "text-embedding-3-large", "family": "embeddings", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2024-01-25", "release_date_source": "changelog", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": true, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Batch", "route": "/v1/batch" }, { "name": "Embeddings", "route": "/v1/embeddings" } ], "tools": [], "features_documented": [], "pricing": { "standard": { "input": 0.13, "_unit": "per 1M tokens" }, "model_page:Embeddings": { "Cost": { "price": 0.13, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "free": { "RPM": 100, "RPD": 2000, "TPM": 40000, "Batch queue limit": null }, "Tier 1": { "RPM": 3000, "RPD": null, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 1000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 5000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 5000000, "Batch queue limit": 500000000 }, "Tier 5": { "RPM": 10000, "RPD": null, "TPM": 10000000, "Batch queue limit": 4000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/text-embedding-3-large", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1705953180, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "text-embedding-3-large is our most capable embedding model for both english and non-english tasks. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/text-embedding-3-large", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-embedding-3-small", "record_kind": "model", "canonical_model": "text-embedding-3-small", "display_name": "text-embedding-3-small", "description": "Small embedding model", "aliases": [], "snapshots": [], "default_snapshot": "text-embedding-3-small", "family": "embeddings", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "flags": [], "release_date": "2024-01-25", "release_date_source": "changelog", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": true, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Batch", "route": "/v1/batch" }, { "name": "Embeddings", "route": "/v1/embeddings" } ], "tools": [], "features_documented": [], "pricing": { "standard": { "input": 0.02, "_unit": "per 1M tokens" }, "model_page:Embeddings": { "Cost": { "price": 0.02, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "free": { "RPM": 100, "RPD": 2000, "TPM": 40000, "Batch queue limit": null }, "Tier 1": { "RPM": 3000, "RPD": null, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 1000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 5000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 5000000, "Batch queue limit": 500000000 }, "Tier 5": { "RPM": 10000, "RPD": null, "TPM": 10000000, "Batch queue limit": 4000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/text-embedding-3-small", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1705948997, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "text-embedding-3-small is our improved, more performant version of our ada embedding model. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/text-embedding-3-small", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-embedding-ada-002", "record_kind": "model", "canonical_model": "text-embedding-ada-002", "display_name": "text-embedding-ada-002", "description": "Older embedding model", "aliases": [], "snapshots": [], "default_snapshot": "text-embedding-ada-002", "family": "embeddings", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "LEGACY" ], "flags": [], "release_date": "2022-12-16", "release_date_source": "GET /v1/models created timestamp (approximation)", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": true, "embeddings": true, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Batch", "route": "/v1/batch" }, { "name": "Embeddings", "route": "/v1/embeddings" } ], "tools": [], "features_documented": [], "pricing": { "standard": { "input": 0.1, "_unit": "per 1M tokens" }, "model_page:Embeddings": { "Cost": { "price": 0.1, "unit": "1M tokens" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD", "TPM", "Batch queue limit" ], "note": null, "tiers": { "free": { "RPM": 100, "RPD": 2000, "TPM": 40000, "Batch queue limit": null }, "Tier 1": { "RPM": 3000, "RPD": null, "TPM": 1000000, "Batch queue limit": 3000000 }, "Tier 2": { "RPM": 5000, "RPD": null, "TPM": 1000000, "Batch queue limit": 20000000 }, "Tier 3": { "RPM": 5000, "RPD": null, "TPM": 5000000, "Batch queue limit": 100000000 }, "Tier 4": { "RPM": 10000, "RPD": null, "TPM": 5000000, "Batch queue limit": 500000000 }, "Tier 5": { "RPM": 10000, "RPD": null, "TPM": 10000000, "Batch queue limit": 4000000000 } } } }, "source": "https://developers.openai.com/api/docs/models/text-embedding-ada-002", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": true, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "openai-internal", "created_ts": 1671217299, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "text-embedding-ada-002 is our improved, more performant version of our ada embedding model. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/text-embedding-ada-002", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-moderation-007", "record_kind": "alias", "canonical_model": "text-moderation-latest", "display_name": "text-moderation (alias text-moderation-007)", "description": "Previous generation text-only moderation model", "aliases": [], "snapshots": [], "default_snapshot": "text-moderation-007", "family": "moderation", "status": [ "DOCUMENTED", "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": "2021-09-01", "context_window": null, "max_input": null, "max_output": 32768, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": true, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Moderation", "route": "/v1/moderations" } ], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "documented_tiers": {}, "source": "https://developers.openai.com/api/docs/models/text-moderation-latest", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2025-04-28", "shutdown_date": "2025-10-27", "replacement": "`omni-moderation`", "phase": "past", "section": "2025-04-28: `text-moderation`", "source": "https://developers.openai.com/api/docs/deprecations#2025-04-28-text-moderation" } ], "shutdown_date": "2025-10-27", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/text-moderation-latest", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-04-28-text-moderation", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-moderation-latest", "record_kind": "model", "canonical_model": "text-moderation-latest", "display_name": "text-moderation", "description": "Previous generation text-only moderation model", "aliases": [ "text-moderation-007" ], "snapshots": [], "default_snapshot": "text-moderation-007", "family": "moderation", "status": [ "DOCUMENTED", "RETIRED", "LEGACY" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": "2021-09-01", "context_window": null, "max_input": null, "max_output": 32768, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": true, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Moderation", "route": "/v1/moderations" } ], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "documented_tiers": {}, "source": "https://developers.openai.com/api/docs/models/text-moderation-latest", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2025-04-28", "shutdown_date": "2025-10-27", "replacement": "`omni-moderation`", "phase": "past", "section": "2025-04-28: `text-moderation`", "source": "https://developers.openai.com/api/docs/deprecations#2025-04-28-text-moderation" } ], "shutdown_date": "2025-10-27", "intro": "Moderation models are free models designed to detect harmful content. This is our text only moderation model; we expect omni-moderation-* models to be the best default moving forward.", "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/text-moderation-latest", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-04-28-text-moderation", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-moderation-stable", "record_kind": "model", "canonical_model": "text-moderation-stable", "display_name": "text-moderation-stable", "description": "Previous generation text-only moderation model", "aliases": [ "text-moderation-007" ], "snapshots": [], "default_snapshot": "text-moderation-007", "family": "moderation", "status": [ "DOCUMENTED", "RETIRED", "LEGACY" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": "2021-09-01", "context_window": null, "max_input": null, "max_output": 32768, "modalities": { "input": [ "text" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": true, "image_in": false, "image_out": false, "audio_in": false, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": true, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Moderation", "route": "/v1/moderations" } ], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "documented_tiers": {}, "source": "https://developers.openai.com/api/docs/models/text-moderation-stable", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": true }, "deprecation": [ { "announced": "2025-04-28", "shutdown_date": "2025-10-27", "replacement": "`omni-moderation`", "phase": "past", "section": "2025-04-28: `text-moderation`", "source": "https://developers.openai.com/api/docs/deprecations#2025-04-28-text-moderation" } ], "shutdown_date": "2025-10-27", "intro": "Moderation models are free models designed to detect harmful content. This is our text only moderation model; we expect omni-moderation-* models to be the best default moving forward.", "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/text-moderation-stable", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2025-04-28-text-moderation", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-search-ada-doc-001", "record_kind": "id_only", "canonical_model": "text-search-ada-doc-001", "display_name": "text-search-ada-doc-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "embeddings", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`text-embedding-3-small`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-search-ada-query-001", "record_kind": "id_only", "canonical_model": "text-search-ada-query-001", "display_name": "text-search-ada-query-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "embeddings", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`text-embedding-3-small`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-search-babbage-doc-001", "record_kind": "id_only", "canonical_model": "text-search-babbage-doc-001", "display_name": "text-search-babbage-doc-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "embeddings", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`text-embedding-3-small`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-search-babbage-query-001", "record_kind": "id_only", "canonical_model": "text-search-babbage-query-001", "display_name": "text-search-babbage-query-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "embeddings", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`text-embedding-3-small`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-search-curie-doc-001", "record_kind": "id_only", "canonical_model": "text-search-curie-doc-001", "display_name": "text-search-curie-doc-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "embeddings", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`text-embedding-3-small`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-search-curie-query-001", "record_kind": "id_only", "canonical_model": "text-search-curie-query-001", "display_name": "text-search-curie-query-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "embeddings", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`text-embedding-3-small`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-search-davinci-doc-001", "record_kind": "id_only", "canonical_model": "text-search-davinci-doc-001", "display_name": "text-search-davinci-doc-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "embeddings", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`text-embedding-3-small`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-search-davinci-query-001", "record_kind": "id_only", "canonical_model": "text-search-davinci-query-001", "display_name": "text-search-davinci-query-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "embeddings", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`text-embedding-3-small`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-similarity-ada-001", "record_kind": "id_only", "canonical_model": "text-similarity-ada-001", "display_name": "text-similarity-ada-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "embeddings", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`text-embedding-3-small`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-similarity-babbage-001", "record_kind": "id_only", "canonical_model": "text-similarity-babbage-001", "display_name": "text-similarity-babbage-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "embeddings", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`text-embedding-3-small`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-similarity-curie-001", "record_kind": "id_only", "canonical_model": "text-similarity-curie-001", "display_name": "text-similarity-curie-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "embeddings", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`text-embedding-3-small`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "text-similarity-davinci-001", "record_kind": "id_only", "canonical_model": "text-similarity-davinci-001", "display_name": "text-similarity-davinci-001", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "embeddings", "status": [ "RETIRED" ], "flags": [], "release_date": null, "release_date_source": null, "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": false, "owned_by": null, "created_ts": null, "openapi_enum": false }, "deprecation": [ { "announced": "2023-07-06", "shutdown_date": "2024-01-04", "replacement": "`text-embedding-3-small`", "phase": "past", "section": "2023-07-06: GPT and embeddings", "source": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings" } ], "shutdown_date": "2024-01-04", "intro": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": null, "http_status": null, "request_note": null }, "sources": [ { "url": "https://developers.openai.com/api/docs/deprecations#2023-07-06-gpt-and-embeddings", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "tts-1", "record_kind": "model", "canonical_model": "tts-1", "display_name": "TTS-1", "description": "Text-to-speech model optimized for speed", "aliases": [], "snapshots": [], "default_snapshot": "tts-1", "family": "text-to-speech", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "LEGACY" ], "flags": [], "release_date": "2023-11-06", "release_date_source": "changelog", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text" ], "output": [ "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": false, "image_in": false, "image_out": false, "audio_in": false, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": true, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Speech generation", "route": "/v1/audio/speech" } ], "tools": [], "features_documented": [], "pricing": { "standard": { "text_input": 15.0, "_unit": "per 1M characters" }, "model_page:Pricing": { "Cost": { "price": 15.0, "unit": "1M characters" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD" ], "note": null, "tiers": { "free": { "RPM": 3, "RPD": 200 }, "Tier 1": { "RPM": 500, "RPD": null }, "Tier 2": { "RPM": 2500, "RPD": null }, "Tier 3": { "RPM": 5000, "RPD": null }, "Tier 4": { "RPM": 7500, "RPD": null }, "Tier 5": { "RPM": 10000, "RPD": null } } } }, "source": "https://developers.openai.com/api/docs/models/tts-1", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "openai-internal", "created_ts": 1681940951, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "TTS is a model that converts text to natural sounding spoken text. The tts-1 model is optimized for realtime text-to-speech use cases. Use it with the Speech endpoint in the Audio API.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/tts-1", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "tts-1-1106", "record_kind": "id_only", "canonical_model": "tts-1-1106", "display_name": "tts-1-1106", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "text-to-speech", "status": [ "LIVE_VERIFIED", "LIVE_DISCOVERED", "LEGACY" ], "flags": [ "DOCUMENTATION_INCOMPLETE" ], "release_date": "2023-11-03", "release_date_source": "GET /v1/models created timestamp (approximation)", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1699053241, "openapi_enum": false }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models/tts-1-1106 -> 200", "get_model": { "status": 200, "id": "tts-1-1106", "object": "model", "created": 1699053241, "owned_by": "system", "shutdown_date": null } }, "sources": [ { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "tts-1-hd", "record_kind": "model", "canonical_model": "tts-1-hd", "display_name": "TTS-1 HD", "description": "Text-to-speech model optimized for quality", "aliases": [], "snapshots": [], "default_snapshot": "tts-1-hd", "family": "text-to-speech", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "LEGACY" ], "flags": [], "release_date": "2023-11-06", "release_date_source": "changelog", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "text" ], "output": [ "audio" ], "unsupported": [] }, "capabilities": { "text_in": true, "text_out": false, "image_in": false, "image_out": false, "audio_in": false, "audio_out": true, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": true, "transcription": false, "translation": false, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Speech generation", "route": "/v1/audio/speech" } ], "tools": [], "features_documented": [], "pricing": { "standard": { "text_input": 30.0, "_unit": "per 1M characters" }, "model_page:Pricing": { "Cost": { "price": 30.0, "unit": "1M characters" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM" ], "note": null, "tiers": { "free": { "RPM": null }, "Tier 1": { "RPM": 500 }, "Tier 2": { "RPM": 2500 }, "Tier 3": { "RPM": 5000 }, "Tier 4": { "RPM": 7500 }, "Tier 5": { "RPM": 10000 } } } }, "source": "https://developers.openai.com/api/docs/models/tts-1-hd", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1699046015, "openapi_enum": true }, "deprecation": [], "shutdown_date": null, "intro": "TTS is a model that converts text to natural sounding spoken text. The tts-1-hd model is optimized for high quality text-to-speech use cases. Use it with the Speech endpoint in the Audio API.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/tts-1-hd", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" }, { "url": "https://developers.openai.com/api/docs/changelog", "retrieved_at": "2026-09-18" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "tts-1-hd-1106", "record_kind": "id_only", "canonical_model": "tts-1-hd-1106", "display_name": "tts-1-hd-1106", "description": null, "aliases": [], "snapshots": [], "default_snapshot": null, "family": "text-to-speech", "status": [ "LIVE_VERIFIED", "LIVE_DISCOVERED", "LEGACY" ], "flags": [ "DOCUMENTATION_INCOMPLETE" ], "release_date": "2023-11-03", "release_date_source": "GET /v1/models created timestamp (approximation)", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [], "output": [], "unsupported": [] }, "capabilities": { "note": "no model page; capabilities unknown" }, "endpoints": [], "tools": [], "features_documented": [], "pricing": { "note": "no price found in pricing.md or model page (retired / not billed / open-weight)" }, "rate_limits": { "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": false, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "system", "created_ts": 1699053533, "openapi_enum": false }, "deprecation": [], "shutdown_date": null, "intro": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "openai", "id": "whisper-1", "record_kind": "model", "canonical_model": "whisper-1", "display_name": "Whisper", "description": "General-purpose speech recognition model", "aliases": [], "snapshots": [], "default_snapshot": "whisper-1", "family": "speech-to-text", "status": [ "DOCUMENTED", "LIVE_VERIFIED", "DEPRECATED", "LEGACY" ], "flags": [], "release_date": "2023-02-27", "release_date_source": "GET /v1/models created timestamp (approximation)", "knowledge_cutoff": null, "context_window": null, "max_input": null, "max_output": null, "modalities": { "input": [ "audio" ], "output": [ "text" ], "unsupported": [] }, "capabilities": { "text_in": false, "text_out": true, "image_in": false, "image_out": false, "audio_in": true, "audio_out": false, "video_in": false, "video_out": false, "reasoning": false, "reasoning_effort_values": null, "reasoning_effort_default": null, "reasoning_mode_pro": false, "streaming": "unknown", "structured_outputs": "unknown", "function_calling": "unknown", "prompt_caching": "unknown", "extended_prompt_cache_retention_24h": false, "explicit_cache_breakpoints": false, "predicted_outputs": "unknown", "file_uploads": "unknown", "evals": "unknown", "stored_completions": "unknown", "distillation": "unknown", "inpainting": false, "fine_tuning": false, "batch": false, "embeddings": false, "realtime": false, "live_sessions": false, "moderation": false, "image_generation_api": false, "image_edit_api": false, "video_generation": false, "speech_generation": false, "transcription": true, "translation": true, "completions_legacy": false, "compaction": "unknown", "long_context_tier_272k": false, "tool_web_search": false, "tool_file_search": false, "tool_code_interpreter": false, "tool_image_generation": false, "tool_mcp": false, "tool_computer_use": false, "tool_hosted_shell": false, "tool_apply_patch": false, "tool_skills": false, "tool_tool_search": false, "tool_function_calling": "unknown", "web_search_feature": false }, "endpoints": [ { "name": "Transcription", "route": "/v1/audio/transcriptions" }, { "name": "Translation", "route": "/v1/audio/translations" } ], "tools": [], "features_documented": [], "pricing": { "standard": { "audio_duration": 0.006, "_unit": "per minute" }, "model_page:Pricing": { "Cost": { "price": 0.006, "unit": "minute" } } }, "rate_limits": { "documented_tiers": { "default": { "metrics": [ "RPM", "RPD" ], "note": null, "tiers": { "free": { "RPM": 3, "RPD": 200 }, "Tier 1": { "RPM": 500, "RPD": null }, "Tier 2": { "RPM": 2500, "RPD": null }, "Tier 3": { "RPM": 5000, "RPD": null }, "Tier 4": { "RPM": 7500, "RPD": null }, "Tier 5": { "RPM": 10000, "RPD": null } } } }, "source": "https://developers.openai.com/api/docs/models/whisper-1", "observed": "see generated/fragments/rate-limits/openai-rate-limits.json#observed (never generalize)" }, "beta_headers": [], "restrictions": null, "availability": { "account": "general (usage-tier based)", "service_tiers": { "standard": true, "batch": false, "flex": false, "fast": false }, "listed_in_get_models": true, "owned_by": "openai-internal", "created_ts": 1677532384, "openapi_enum": true }, "deprecation": [ { "announced": "2026-08-26", "shutdown_date": "2027-02-26", "replacement": "`gpt-live-transcribe` or `gpt-transcribe`", "phase": "upcoming", "section": "2026-08-26: Transcription models", "source": "https://developers.openai.com/api/docs/deprecations#2026-08-26-transcription-models" }, { "announced": null, "shutdown_date": "2027-02-26", "replacement": null, "phase": "live", "section": "GET /v1/models shutdown_date field", "source": "https://api.openai.com/v1/models" } ], "shutdown_date": "2027-02-26", "intro": "Whisper is a general-purpose speech recognition model, trained on a large dataset of diverse audio. You can also use it as a multitask model to perform multilingual speech recognition as well as speech translation and language identification.", "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "id present in GET /v1/models listing (2026-09-18)" }, "sources": [ { "url": "https://developers.openai.com/api/docs/models/whisper-1", "retrieved_at": "2026-09-18" }, { "url": "https://api.openai.com/v1/models", "retrieved_at": "2026-09-18", "note": "GET /v1/models (live listing)" }, { "url": "https://developers.openai.com/api/docs/pricing", "retrieved_at": "2026-09-18" }, { "url": "https://developers.openai.com/api/docs/deprecations#2026-08-26-transcription-models", "retrieved_at": "2026-09-18" }, { "url": "https://github.com/openai/openai-openapi (openapi-master.yaml, downloaded 2026-09-18)", "retrieved_at": "2026-09-18", "note": "id appears in an OpenAPI enum" } ], "_fragment": "generated/fragments/models/openai-models.json" }, { "provider": "xai", "id": "grok-4.6", "display_name": "Grok 4.6", "kind": "model", "aliases": [], "snapshots": [ "grok-4.6" ], "family": "Grok 4.x", "generation": "4.6", "description": "SpaceXAI's frontier model for coding, agentic tasks, and knowledge work. No text output limit. Recommended default for code and chat.", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "release_date": "2026-08 (release notes, August 2026)", "created_at_live": "2026-08-06", "fingerprint_live": "fp_9a755add8c", "version_live": "1.0", "knowledge_cutoff": "2026-02-01", "context_window": 500000, "context_window_note": "long-context pricing above 200,000 prompt tokens", "max_output": null, "max_output_note": "no documented text output limit (grok-4.6 page: 'No text output limit'); other models: not documented", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "text_input": true, "image_input": true, "text_output": true, "reasoning": true, "reasoning_always_on": true, "reasoning_can_be_disabled": false, "reasoning_effort_parameter": true, "reasoning_effort_levels": [ "low", "medium", "high", "xhigh" ], "reasoning_effort_default": "high", "encrypted_reasoning_content": "some models (Responses include: reasoning.encrypted_content)", "function_calling": true, "parallel_tool_calls": true, "structured_outputs": true, "streaming": true, "logprobs": false, "prompt_caching_automatic": true, "prompt_cache_key_or_x_grok_conv_id": true, "batch_api": false, "deferred_completions": true, "priority_processing": true, "context_compaction": true, "websocket_responses": true, "files_attachments": true, "collections_search": true, "server_side_tools": true, "web_search": true, "x_search": true, "code_execution": true, "remote_mcp": "unknown", "image_generation_tool": "unknown", "fine_tuning": false, "embeddings": false, "audio_input": false, "voice_realtime": false, "video_output": false, "image_output": false, "anthropic_messages_compat": true }, "endpoints": [ "POST /v1/chat/completions", "POST /v1/responses", "POST /v1/responses/compact", "WS wss://api.x.ai/v1/responses", "POST /v1/messages (Anthropic-compatible)", "GET /v1/chat/deferred-completion/{request_id}", "POST /v1/tokenize-text", "Batch API (/v1/batches, gRPC BatchMgmt)" ], "tools": [ "function", "web_search", "x_search", "code_execution", "code_interpreter", "image_generation", "attachment_search", "collections_search", "file_search", "view_image", "view_x_video", "mcp" ], "pricing": { "unit": "USD per 1M tokens", "standard": { "input": 2.0, "cached_input": 0.5, "image_input": 2.0, "output": 6.0, "applies": "prompt < 200,000 tokens" }, "long_context": { "input": 4.0, "cached_input": 1.0, "output": 12.0, "applies": "prompt >= 200,000 tokens: the higher rate is billed for ALL tokens of the request" }, "batch_discount": null, "priority_multiplier": 2.0, "us_regional_multiplier": 1.1, "search_price_live": 0, "live_raw_ticks": { "prompt_text_token_price": 20000, "cached_prompt_text_token_price": 5000, "prompt_image_token_price": 20000, "completion_text_token_price": 60000, "search_price": 0, "prompt_text_token_price_long_context": 40000, "cached_prompt_text_token_price_long_context": 10000, "completion_text_token_price_long_context": 120000, "long_context_threshold": 200000 } }, "rate_limits": { "documented": { "tier_rps_T0_T4": [ 150, 172, 208, 312, 500 ], "tier_tpm_T0_T4": [ "50M", "53M", "60M", "74M", "100M" ], "unit": "RPS = requests per second (derived from RPM/60); TPM counts prompt+completion+reasoning+cached tokens" }, "observed_headers_2026_09_19": { "x-ratelimit-limit-requests": "7200", "x-ratelimit-limit-tokens": "50000000" } }, "beta_headers": [], "restrictions": [ "xhigh reasoning effort is available on grok-4.6 and later", "reasoning summaries exposed (reasoning_content deltas when streaming)", "logprobs/top_logprobs silently ignored (grok-4.20 and newer)", "only model on https://us.api.x.ai/v1 (1.1x token prices)" ], "availability": { "account": "available to our team (Tier 0)", "regions": [ "us-east-1", "us-west-2", "us-central-1" ], "base_urls": [ "https://api.x.ai/v1", "https://us.api.x.ai/v1" ], "gateways": [ "Vercel AI Gateway", "OpenRouter", "Cloudflare", "Google Cloud Vertex AI (partner model)", "Microsoft Foundry" ] }, "live_usage_shape": { "prompt_tokens": 640, "completion_tokens": 1, "reasoning_tokens": 91, "cached_tokens": 512, "total_tokens": 732, "cost_in_usd_ticks": 10640000, "reasoning_content_returned": true }, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models + GET /v1/language-models (2026-09-19) and one minimal POST (see live_usage_shape)" }, "sources": [ { "url": "https://docs.x.ai/developers/models", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/models/grok-4.6", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/pricing", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rate-limits", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/model-capabilities/text/reasoning", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rest-api-reference/inference/models", "retrieved_at": "2026-09-19" }, { "url": "https://api.x.ai/v1/language-models", "retrieved_at": "2026-09-19", "note": "live 2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-4.5", "display_name": "Grok 4.5", "kind": "model", "aliases": [ "grok-4.5-latest", "grok-build-latest" ], "snapshots": [ "grok-4.5" ], "family": "Grok 4.x", "generation": "4.5", "description": "Intelligent coding model for agentic software, engineering and workflow tasks (trained in Memphis with new science/engineering/math datasets).", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "release_date": "2026-07 (release notes, July 2026; EU console availability announced same month)", "created_at_live": "2026-06-29", "fingerprint_live": "fp_7fd98326f4", "version_live": "1.0", "knowledge_cutoff": null, "context_window": 500000, "context_window_note": "long-context pricing above 200,000 prompt tokens", "max_output": null, "max_output_note": "no documented text output limit (grok-4.6 page: 'No text output limit'); other models: not documented", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "text_input": true, "image_input": true, "text_output": true, "reasoning": true, "reasoning_always_on": true, "reasoning_can_be_disabled": false, "reasoning_effort_parameter": true, "reasoning_effort_levels": [ "low", "medium", "high", "xhigh" ], "reasoning_effort_default": "high", "encrypted_reasoning_content": "some models (Responses include: reasoning.encrypted_content)", "function_calling": true, "parallel_tool_calls": true, "structured_outputs": true, "streaming": true, "logprobs": false, "prompt_caching_automatic": true, "prompt_cache_key_or_x_grok_conv_id": true, "batch_api": false, "deferred_completions": true, "priority_processing": true, "context_compaction": true, "websocket_responses": true, "files_attachments": true, "collections_search": true, "server_side_tools": "unknown (docs only list tools on the grok-4.6 page; tools overview examples use grok-4.6)", "web_search": "unknown", "x_search": "unknown", "code_execution": "unknown", "remote_mcp": "unknown", "image_generation_tool": "unknown", "fine_tuning": false, "embeddings": false, "audio_input": false, "voice_realtime": false, "video_output": false, "image_output": false, "anthropic_messages_compat": true }, "endpoints": [ "POST /v1/chat/completions", "POST /v1/responses", "POST /v1/responses/compact", "WS wss://api.x.ai/v1/responses", "POST /v1/messages (Anthropic-compatible)", "GET /v1/chat/deferred-completion/{request_id}", "POST /v1/tokenize-text", "Batch API (/v1/batches, gRPC BatchMgmt)" ], "tools": [ "function", "web_search", "x_search", "code_execution", "code_interpreter", "image_generation", "attachment_search", "collections_search", "file_search", "view_image", "view_x_video", "mcp" ], "pricing": { "unit": "USD per 1M tokens", "standard": { "input": 2.0, "cached_input": 0.3, "image_input": 2.0, "output": 6.0, "applies": "prompt < 200,000 tokens" }, "long_context": { "input": 4.0, "cached_input": 0.6, "output": 12.0, "applies": "prompt >= 200,000 tokens: the higher rate is billed for ALL tokens of the request" }, "batch_discount": null, "priority_multiplier": 2.0, "us_regional_multiplier": null, "search_price_live": 0, "live_raw_ticks": { "prompt_text_token_price": 20000, "cached_prompt_text_token_price": 3000, "prompt_image_token_price": 20000, "completion_text_token_price": 60000, "search_price": 0, "prompt_text_token_price_long_context": 40000, "cached_prompt_text_token_price_long_context": 6000, "completion_text_token_price_long_context": 120000, "long_context_threshold": 200000 } }, "rate_limits": { "documented": { "tier_rps_T0_T4": [ 150, 172, 208, 312, 500 ], "tier_tpm_T0_T4": [ "50M", "53M", "60M", "74M", "100M" ], "unit": "RPS = requests per second (derived from RPM/60); TPM counts prompt+completion+reasoning+cached tokens" }, "observed_headers_2026_09_19": { "x-ratelimit-limit-requests": "7200", "x-ratelimit-limit-tokens": "50000000" } }, "beta_headers": [], "restrictions": [ "reasoning page: supports low/medium/high only and 'xhigh' is treated as 'high'; the model page lists xhigh as supported - discrepancy recorded", "aliases grok-4.5-latest and grok-build-latest (live)" ], "availability": { "account": "available to our team (Tier 0)", "regions": [ "us-east-1", "us-west-2" ], "base_urls": [ "https://api.x.ai/v1" ], "gateways": "unknown" }, "live_usage_shape": { "prompt_tokens": 498, "completion_tokens": 1, "reasoning_tokens": 55, "cached_tokens": 384, "total_tokens": 554, "cost_in_usd_ticks": 6792000, "reasoning_content_returned": true }, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models + GET /v1/language-models (2026-09-19) and one minimal POST (see live_usage_shape)" }, "sources": [ { "url": "https://docs.x.ai/developers/models", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/models/grok-4.5", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/pricing", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rate-limits", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/model-capabilities/text/reasoning", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rest-api-reference/inference/models", "retrieved_at": "2026-09-19" }, { "url": "https://api.x.ai/v1/language-models", "retrieved_at": "2026-09-19", "note": "live 2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-4.3", "display_name": "Grok 4.3", "kind": "model", "aliases": [ "grok-4.3-latest" ], "snapshots": [ "grok-4.3" ], "family": "Grok 4.x", "generation": "4.3", "description": "Fast, reliable model with strong tool calling and instruction following; 1M context; 4-5 reasoning effort levels incl. none. Redirect target of the models retired on 2026-05-15.", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "release_date": "2026-04 (created 2026-04-17 live; migration guide names it the May-15 redirect target)", "created_at_live": "2026-04-17", "fingerprint_live": "fp_0e35aa9326", "version_live": "1.0", "knowledge_cutoff": null, "context_window": 1000000, "context_window_note": "long-context pricing above 200,000 prompt tokens", "max_output": null, "max_output_note": "no documented text output limit (grok-4.6 page: 'No text output limit'); other models: not documented", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "text_input": true, "image_input": true, "text_output": true, "reasoning": true, "reasoning_always_on": false, "reasoning_can_be_disabled": true, "reasoning_effort_parameter": true, "reasoning_effort_levels": [ "none", "low", "medium", "high", "xhigh" ], "reasoning_effort_default": "low", "encrypted_reasoning_content": "some models (Responses include: reasoning.encrypted_content)", "function_calling": true, "parallel_tool_calls": true, "structured_outputs": true, "streaming": true, "logprobs": false, "prompt_caching_automatic": true, "prompt_cache_key_or_x_grok_conv_id": true, "batch_api": true, "deferred_completions": true, "priority_processing": true, "context_compaction": true, "websocket_responses": true, "files_attachments": true, "collections_search": true, "server_side_tools": "unknown (docs only list tools on the grok-4.6 page; tools overview examples use grok-4.6)", "web_search": "unknown", "x_search": "unknown", "code_execution": "unknown", "remote_mcp": "unknown", "image_generation_tool": "unknown", "fine_tuning": false, "embeddings": false, "audio_input": false, "voice_realtime": false, "video_output": false, "image_output": false, "anthropic_messages_compat": true }, "endpoints": [ "POST /v1/chat/completions", "POST /v1/responses", "POST /v1/responses/compact", "WS wss://api.x.ai/v1/responses", "POST /v1/messages (Anthropic-compatible)", "GET /v1/chat/deferred-completion/{request_id}", "POST /v1/tokenize-text", "Batch API (/v1/batches, gRPC BatchMgmt)" ], "tools": [ "function", "web_search", "x_search", "code_execution", "code_interpreter", "image_generation", "attachment_search", "collections_search", "file_search", "view_image", "view_x_video", "mcp" ], "pricing": { "unit": "USD per 1M tokens", "standard": { "input": 1.25, "cached_input": 0.2, "image_input": 1.25, "output": 2.5, "applies": "prompt < 200,000 tokens" }, "long_context": { "input": 2.5, "cached_input": 0.4, "output": 5.0, "applies": "prompt >= 200,000 tokens: the higher rate is billed for ALL tokens of the request" }, "batch_discount": 0.2, "priority_multiplier": 2.0, "us_regional_multiplier": null, "search_price_live": 0, "live_raw_ticks": { "prompt_text_token_price": 12500, "cached_prompt_text_token_price": 2000, "prompt_image_token_price": 12500, "completion_text_token_price": 25000, "search_price": 0, "prompt_text_token_price_long_context": 25000, "cached_prompt_text_token_price_long_context": 4000, "completion_text_token_price_long_context": 50000, "long_context_threshold": 200000 } }, "rate_limits": { "documented": { "tier_rps_T0_T4": [ 37, 50, 75, 125, 208 ], "tier_tpm_T0_T4": [ "10M", "15M", "25M", "45M", "85M" ], "unit": "RPS = requests per second (derived from RPM/60); TPM counts prompt+completion+reasoning+cached tokens" }, "observed_headers_2026_09_19": { "x-ratelimit-limit-requests": "1800", "x-ratelimit-limit-tokens": "10000000" } }, "beta_headers": [], "restrictions": [ "reasoning_effort='none' accepted live (0 reasoning tokens)", "only model returned by GET https://eu-west-1.api.x.ai/v1/models (LIVE_DISCOVERED, undocumented base URL)", "cheapest current text model; used for this atlas's probes" ], "availability": { "account": "available to our team (Tier 0)", "regions": [ "us-east-1", "eu-west-1", "us-west-2" ], "base_urls": [ "https://api.x.ai/v1", "https://eu-west-1.api.x.ai/v1 (LIVE_DISCOVERED)" ], "gateways": "unknown" }, "live_usage_shape": { "prompt_tokens": 188, "completion_tokens": 2, "reasoning_tokens": 0, "cached_tokens": 128, "total_tokens": 190, "cost_in_usd_ticks": 1056000, "reasoning_content_returned": false, "request_note": "reasoning_effort=none accepted" }, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models + GET /v1/language-models (2026-09-19) and one minimal POST (see live_usage_shape)" }, "sources": [ { "url": "https://docs.x.ai/developers/models", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/models/grok-4.3", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/pricing", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rate-limits", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/model-capabilities/text/reasoning", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rest-api-reference/inference/models", "retrieved_at": "2026-09-19" }, { "url": "https://api.x.ai/v1/language-models", "retrieved_at": "2026-09-19", "note": "live 2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-4.20-0309-reasoning", "display_name": "Grok 4.20 (reasoning)", "kind": "model", "aliases": [ "grok-4.20-reasoning-latest", "grok-4.20", "grok-4.20-reasoning", "grok-4.20-0309", "grok-4.20-beta-0309-reasoning", "grok-4.20-beta", "grok-4.20-beta-0309", "grok-4.20-beta-latest", "grok-4.20-beta-latest-reasoning", "grok-4.20-beta-reasoning", "grok-4.20-experimental-beta-0304-reasoning", "grok-4.20-experimental-beta-0304", "grok-4.20-experimental-beta-reasoning-latest", "grok-4.20-experimental-beta-latest", "grok-4.20-reasoning-gv2" ], "snapshots": [ "grok-4.20-0309-reasoning" ], "family": "Grok 4.20", "generation": "4.20", "description": "High-performance model with industry-leading speed and agentic tool calling; lowest hallucination rate claim; strict prompt adherence.", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "release_date": "2026-03-09 (created; release notes March 2026)", "created_at_live": "2026-03-09", "fingerprint_live": "fp_573f14d505", "version_live": "1.0", "knowledge_cutoff": null, "context_window": 1000000, "context_window_note": "long-context pricing above 200,000 prompt tokens", "max_output": null, "max_output_note": "no documented text output limit (grok-4.6 page: 'No text output limit'); other models: not documented", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "text_input": true, "image_input": true, "text_output": true, "reasoning": true, "reasoning_always_on": true, "reasoning_can_be_disabled": false, "reasoning_effort_parameter": false, "reasoning_effort_levels": null, "reasoning_effort_default": null, "encrypted_reasoning_content": "some models (Responses include: reasoning.encrypted_content)", "function_calling": true, "parallel_tool_calls": true, "structured_outputs": true, "streaming": true, "logprobs": false, "prompt_caching_automatic": true, "prompt_cache_key_or_x_grok_conv_id": true, "batch_api": true, "deferred_completions": true, "priority_processing": true, "context_compaction": true, "websocket_responses": true, "files_attachments": true, "collections_search": true, "server_side_tools": "unknown (docs only list tools on the grok-4.6 page; tools overview examples use grok-4.6)", "web_search": "unknown", "x_search": "unknown", "code_execution": "unknown", "remote_mcp": "unknown", "image_generation_tool": "unknown", "fine_tuning": false, "embeddings": false, "audio_input": false, "voice_realtime": false, "video_output": false, "image_output": false, "anthropic_messages_compat": true }, "endpoints": [ "POST /v1/chat/completions", "POST /v1/responses", "POST /v1/responses/compact", "WS wss://api.x.ai/v1/responses", "POST /v1/messages (Anthropic-compatible)", "GET /v1/chat/deferred-completion/{request_id}", "POST /v1/tokenize-text", "Batch API (/v1/batches, gRPC BatchMgmt)" ], "tools": [ "function", "web_search", "x_search", "code_execution", "code_interpreter", "image_generation", "attachment_search", "collections_search", "file_search", "view_image", "view_x_video", "mcp" ], "pricing": { "unit": "USD per 1M tokens", "standard": { "input": 1.25, "cached_input": 0.2, "image_input": 1.25, "output": 2.5, "applies": "prompt < 200,000 tokens" }, "long_context": { "input": 2.5, "cached_input": 0.4, "output": 5.0, "applies": "prompt >= 200,000 tokens: the higher rate is billed for ALL tokens of the request" }, "batch_discount": 0.2, "priority_multiplier": 2.0, "us_regional_multiplier": null, "search_price_live": 0, "live_raw_ticks": { "prompt_text_token_price": 12500, "cached_prompt_text_token_price": 2000, "prompt_image_token_price": 12500, "completion_text_token_price": 25000, "search_price": 0, "prompt_text_token_price_long_context": 25000, "cached_prompt_text_token_price_long_context": 4000, "completion_text_token_price_long_context": 50000, "long_context_threshold": 200000 } }, "rate_limits": { "documented": { "tier_rps_T0_T4": [ 37, 50, 75, 125, 208 ], "tier_tpm_T0_T4": [ "10M", "15M", "25M", "45M", "85M" ], "unit": "RPS = requests per second (derived from RPM/60); TPM counts prompt+completion+reasoning+cached tokens" }, "observed_headers_2026_09_19": null }, "beta_headers": [], "restrictions": [ "reasoning_effort rejected live: 400 invalid-argument 'Model grok-4.20-0309-reasoning does not support parameter reasoningEffort'", "15 aliases incl. grok-4.20, grok-4.20-beta, grok-4.20-reasoning-gv2" ], "availability": { "account": "available to our team (Tier 0)", "regions": [ "us-east-1", "us-west-2" ], "base_urls": [ "https://api.x.ai/v1" ], "gateways": "unknown" }, "live_usage_shape": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models + GET /v1/language-models (2026-09-19) and one minimal POST (see live_usage_shape)" }, "sources": [ { "url": "https://docs.x.ai/developers/models", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/models/grok-4.20-0309-reasoning", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/pricing", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rate-limits", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/model-capabilities/text/reasoning", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rest-api-reference/inference/models", "retrieved_at": "2026-09-19" }, { "url": "https://api.x.ai/v1/language-models", "retrieved_at": "2026-09-19", "note": "live 2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-4.20-0309-non-reasoning", "display_name": "Grok 4.20 (non-reasoning)", "kind": "model", "aliases": [ "grok-4.20-non-reasoning", "grok-4.20-non-reasoning-latest", "grok-4.20-beta-non-reasoning", "grok-4.20-beta-latest-non-reasoning", "grok-4.20-experimental-beta-0304-non-reasoning", "grok-4.20-experimental-beta-non-reasoning-latest", "grok-4.20-beta-0309-non-reasoning", "grok-4.20-non-reasoning-gv2" ], "snapshots": [ "grok-4.20-0309-non-reasoning" ], "family": "Grok 4.20", "generation": "4.20", "description": "Non-reasoning variant of Grok 4.20 (no reasoning tokens).", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "release_date": "2026-03-09 (created; release notes March 2026)", "created_at_live": "2026-03-09", "fingerprint_live": "fp_babf5254ba", "version_live": "1.0", "knowledge_cutoff": null, "context_window": 1000000, "context_window_note": "long-context pricing above 200,000 prompt tokens", "max_output": null, "max_output_note": "no documented text output limit (grok-4.6 page: 'No text output limit'); other models: not documented", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "text_input": true, "image_input": true, "text_output": true, "reasoning": false, "reasoning_always_on": false, "reasoning_can_be_disabled": false, "reasoning_effort_parameter": false, "reasoning_effort_levels": null, "reasoning_effort_default": null, "encrypted_reasoning_content": "some models (Responses include: reasoning.encrypted_content)", "function_calling": true, "parallel_tool_calls": true, "structured_outputs": true, "streaming": true, "logprobs": false, "prompt_caching_automatic": true, "prompt_cache_key_or_x_grok_conv_id": true, "batch_api": true, "deferred_completions": true, "priority_processing": true, "context_compaction": true, "websocket_responses": true, "files_attachments": true, "collections_search": true, "server_side_tools": "unknown (docs only list tools on the grok-4.6 page; tools overview examples use grok-4.6)", "web_search": "unknown", "x_search": "unknown", "code_execution": "unknown", "remote_mcp": "unknown", "image_generation_tool": "unknown", "fine_tuning": false, "embeddings": false, "audio_input": false, "voice_realtime": false, "video_output": false, "image_output": false, "anthropic_messages_compat": true }, "endpoints": [ "POST /v1/chat/completions", "POST /v1/responses", "POST /v1/responses/compact", "WS wss://api.x.ai/v1/responses", "POST /v1/messages (Anthropic-compatible)", "GET /v1/chat/deferred-completion/{request_id}", "POST /v1/tokenize-text", "Batch API (/v1/batches, gRPC BatchMgmt)" ], "tools": [ "function", "web_search", "x_search", "code_execution", "code_interpreter", "image_generation", "attachment_search", "collections_search", "file_search", "view_image", "view_x_video", "mcp" ], "pricing": { "unit": "USD per 1M tokens", "standard": { "input": 1.25, "cached_input": 0.2, "image_input": 1.25, "output": 2.5, "applies": "prompt < 200,000 tokens" }, "long_context": { "input": 2.5, "cached_input": 0.4, "output": 5.0, "applies": "prompt >= 200,000 tokens: the higher rate is billed for ALL tokens of the request" }, "batch_discount": 0.2, "priority_multiplier": 2.0, "us_regional_multiplier": null, "search_price_live": 0, "live_raw_ticks": { "prompt_text_token_price": 12500, "cached_prompt_text_token_price": 2000, "prompt_image_token_price": 12500, "completion_text_token_price": 25000, "search_price": 0, "prompt_text_token_price_long_context": 25000, "cached_prompt_text_token_price_long_context": 4000, "completion_text_token_price_long_context": 50000, "long_context_threshold": 200000 } }, "rate_limits": { "documented": { "tier_rps_T0_T4": [ 37, 50, 75, 125, 208 ], "tier_tpm_T0_T4": [ "10M", "15M", "25M", "45M", "85M" ], "unit": "RPS = requests per second (derived from RPM/60); TPM counts prompt+completion+reasoning+cached tokens" }, "observed_headers_2026_09_19": { "x-ratelimit-limit-requests": "1800", "x-ratelimit-limit-tokens": "10000000" } }, "beta_headers": [], "restrictions": [ "reasoning_effort rejected live (400 invalid-argument)", "usage.completion_tokens_details.reasoning_tokens = 0 live" ], "availability": { "account": "available to our team (Tier 0)", "regions": [ "us-east-1", "us-west-2" ], "base_urls": [ "https://api.x.ai/v1" ], "gateways": "unknown" }, "live_usage_shape": { "prompt_tokens": 188, "completion_tokens": 2, "reasoning_tokens": 0, "cached_tokens": 128, "total_tokens": 190, "cost_in_usd_ticks": 1056000, "reasoning_content_returned": false }, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models + GET /v1/language-models (2026-09-19) and one minimal POST (see live_usage_shape)" }, "sources": [ { "url": "https://docs.x.ai/developers/models", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/models/grok-4.20-0309-non-reasoning", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/pricing", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rate-limits", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/model-capabilities/text/reasoning", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rest-api-reference/inference/models", "retrieved_at": "2026-09-19" }, { "url": "https://api.x.ai/v1/language-models", "retrieved_at": "2026-09-19", "note": "live 2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-4.20-multi-agent-0309", "display_name": "Grok 4.20 Multi-Agent (beta)", "kind": "model", "aliases": [ "grok-4.20-multi-agent", "grok-4.20-multi-agent-latest", "grok-4.20-multi-agent-beta-latest", "grok-4.20-multi-agent-experimental-beta-0304", "grok-4.20-multi-agent-experimental-beta-latest", "grok-4.20-multi-agent-beta-0309" ], "snapshots": [ "grok-4.20-multi-agent-0309" ], "family": "Grok 4.20", "generation": "4.20", "description": "Multiple agents collaborate in parallel to perform deep research tasks. Responses API only.", "status": [ "DOCUMENTED", "BETA", "LIVE_VERIFIED" ], "release_date": "2026-03 (release notes March 2026)", "created_at_live": "2026-03-09", "fingerprint_live": "fp_ea62c4204b", "version_live": "1.0", "knowledge_cutoff": null, "context_window": 1000000, "context_window_note": "long-context pricing above 200,000 prompt tokens", "max_output": null, "max_output_note": "no documented text output limit (grok-4.6 page: 'No text output limit'); other models: not documented", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "text_input": true, "image_input": true, "text_output": true, "reasoning": true, "reasoning_always_on": true, "reasoning_can_be_disabled": false, "reasoning_effort_parameter": "reasoning.effort controls agent count (low/medium = 4 agents, high/xhigh = 16), not reasoning depth", "reasoning_effort_levels": [ "low", "medium", "high", "xhigh" ], "reasoning_effort_default": "medium (observed in response.reasoning.effort)", "encrypted_reasoning_content": "some models (Responses include: reasoning.encrypted_content)", "function_calling": true, "parallel_tool_calls": true, "structured_outputs": true, "streaming": true, "logprobs": false, "prompt_caching_automatic": true, "prompt_cache_key_or_x_grok_conv_id": true, "batch_api": true, "deferred_completions": false, "priority_processing": false, "context_compaction": true, "websocket_responses": true, "files_attachments": true, "collections_search": true, "server_side_tools": "unknown (docs only list tools on the grok-4.6 page; tools overview examples use grok-4.6)", "web_search": "unknown", "x_search": "unknown", "code_execution": "unknown", "remote_mcp": "unknown", "image_generation_tool": "unknown", "fine_tuning": false, "embeddings": false, "audio_input": false, "voice_realtime": false, "video_output": false, "image_output": false, "anthropic_messages_compat": true }, "endpoints": [ "POST /v1/responses", "Batch API" ], "tools": [ "function", "web_search", "x_search", "code_execution", "code_interpreter", "image_generation", "attachment_search", "collections_search", "file_search", "view_image", "view_x_video", "mcp" ], "pricing": { "unit": "USD per 1M tokens", "standard": { "input": 1.25, "cached_input": 0.2, "image_input": 1.25, "output": 2.5, "applies": "prompt < 200,000 tokens" }, "long_context": { "input": 2.5, "cached_input": 0.4, "output": 5.0, "applies": "prompt >= 200,000 tokens: the higher rate is billed for ALL tokens of the request" }, "batch_discount": 0.2, "priority_multiplier": "2.0 (Chat Completions/Responses; not documented per model)", "us_regional_multiplier": null, "search_price_live": 0, "live_raw_ticks": { "prompt_text_token_price": 12500, "cached_prompt_text_token_price": 2000, "prompt_image_token_price": 12500, "completion_text_token_price": 25000, "search_price": 0, "prompt_text_token_price_long_context": 25000, "cached_prompt_text_token_price_long_context": 4000, "completion_text_token_price_long_context": 50000, "long_context_threshold": 200000 } }, "rate_limits": { "documented": { "tier_rps_T0_T4": [ 9, 12, 18, 31, 56 ], "tier_tpm_T0_T4": [ "2.5M", "3.7M", "6.2M", "11M", "21M" ], "unit": "RPS = requests per second (derived from RPM/60); TPM counts prompt+completion+reasoning+cached tokens" }, "observed_headers_2026_09_19": null }, "beta_headers": [], "restrictions": [ "POST /v1/chat/completions -> 400 'Multi Agent requests are not allowed on chat completions' (live)", "output text ended with a '\\\\confidence{NN}' marker in both live probes", "usage.context_details{input_tokens,output_tokens} present (undocumented)" ], "availability": { "account": "available to our team (Tier 0)", "regions": [ "us-east-1", "us-west-2" ], "base_urls": [ "https://api.x.ai/v1" ], "gateways": "unknown" }, "live_usage_shape": { "endpoint": "POST /v1/responses (chat/completions -> 400 'Multi Agent requests are not allowed on chat completions')", "input_tokens": 2655, "cached_tokens": 2560, "output_tokens": 1645, "reasoning_tokens": 1618, "total_tokens": 4300, "num_server_side_tools_used": 0, "cost_in_usd_ticks": 47432500, "reasoning_effort_reported": "medium", "context_details": { "input_tokens": 647, "output_tokens": 388 }, "output_text": "OK\\n\\n\\n\\\\confidence{80}" }, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models + GET /v1/language-models (2026-09-19) and one minimal POST (see live_usage_shape)" }, "sources": [ { "url": "https://docs.x.ai/developers/models", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/models/grok-4.20-multi-agent-0309", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/pricing", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rate-limits", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/model-capabilities/text/reasoning", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rest-api-reference/inference/models", "retrieved_at": "2026-09-19" }, { "url": "https://api.x.ai/v1/language-models", "retrieved_at": "2026-09-19", "note": "live 2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-build-0.1", "display_name": "Grok Build 0.1", "kind": "model", "aliases": [ "grok-code-fast-1", "grok-code-fast", "grok-code-fast-1-0825" ], "snapshots": [ "grok-build-0.1" ], "family": "Build", "generation": "0.1", "description": "Coding model trained for agentic coding workflows; default model of the Grok Build CLI. Redirect target of grok-code-fast-1 (now an alias).", "status": [ "DOCUMENTED", "PREVIEW", "LIVE_VERIFIED" ], "release_date": "2026-05 (release notes May 2026, 'early access'); created 2026-04-16 live", "created_at_live": "2026-04-16", "fingerprint_live": "fp_b8df82e993", "version_live": "1.0", "knowledge_cutoff": null, "context_window": 256000, "context_window_note": "long-context pricing above 200,000 prompt tokens", "max_output": null, "max_output_note": "no documented text output limit (grok-4.6 page: 'No text output limit'); other models: not documented", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "text_input": true, "image_input": true, "text_output": true, "reasoning": true, "reasoning_always_on": true, "reasoning_can_be_disabled": false, "reasoning_effort_parameter": false, "reasoning_effort_levels": null, "reasoning_effort_default": null, "encrypted_reasoning_content": "some models (Responses include: reasoning.encrypted_content)", "function_calling": true, "parallel_tool_calls": true, "structured_outputs": true, "streaming": true, "logprobs": "unknown", "prompt_caching_automatic": true, "prompt_cache_key_or_x_grok_conv_id": true, "batch_api": false, "deferred_completions": true, "priority_processing": true, "context_compaction": true, "websocket_responses": true, "files_attachments": true, "collections_search": true, "server_side_tools": "unknown (docs only list tools on the grok-4.6 page; tools overview examples use grok-4.6)", "web_search": "unknown", "x_search": "unknown", "code_execution": "unknown", "remote_mcp": "unknown", "image_generation_tool": "unknown", "fine_tuning": false, "embeddings": false, "audio_input": false, "voice_realtime": false, "video_output": false, "image_output": false, "anthropic_messages_compat": true }, "endpoints": [ "POST /v1/chat/completions", "POST /v1/responses", "POST /v1/responses/compact", "WS wss://api.x.ai/v1/responses", "POST /v1/messages (Anthropic-compatible)", "GET /v1/chat/deferred-completion/{request_id}", "POST /v1/tokenize-text", "Batch API (/v1/batches, gRPC BatchMgmt)" ], "tools": [ "function", "web_search", "x_search", "code_execution", "code_interpreter", "image_generation", "attachment_search", "collections_search", "file_search", "view_image", "view_x_video", "mcp" ], "pricing": { "unit": "USD per 1M tokens", "standard": { "input": 1.0, "cached_input": 0.2, "image_input": 1.0, "output": 2.0, "applies": "prompt < 200,000 tokens" }, "long_context": { "input": 2.0, "cached_input": 0.4, "output": 4.0, "applies": "prompt >= 200,000 tokens: the higher rate is billed for ALL tokens of the request" }, "batch_discount": null, "priority_multiplier": 2.0, "us_regional_multiplier": null, "search_price_live": 0, "live_raw_ticks": { "prompt_text_token_price": 10000, "cached_prompt_text_token_price": 2000, "prompt_image_token_price": 10000, "completion_text_token_price": 20000, "search_price": 0, "prompt_text_token_price_long_context": 20000, "cached_prompt_text_token_price_long_context": 4000, "completion_text_token_price_long_context": 40000, "long_context_threshold": 200000 } }, "rate_limits": { "documented": { "tier_rps_T0_T4": [ 37, 50, 75, 125, 208 ], "tier_tpm_T0_T4": [ "10M", "15M", "25M", "45M", "85M" ], "unit": "RPS = requests per second (derived from RPM/60); TPM counts prompt+completion+reasoning+cached tokens" }, "observed_headers_2026_09_19": { "x-ratelimit-limit-requests": "1800", "x-ratelimit-limit-tokens": "10000000" } }, "beta_headers": [], "restrictions": [ "reasoning_effort rejected live (400 invalid-argument)", "aliases grok-code-fast-1, grok-code-fast, grok-code-fast-1-0825 resolve to it (GET /v1/models/grok-code-fast-1 returns id grok-build-0.1)" ], "availability": { "account": "available to our team (Tier 0)", "regions": [ "us-east-1", "us-west-2" ], "base_urls": [ "https://api.x.ai/v1" ], "gateways": "unknown" }, "live_usage_shape": { "prompt_tokens": 190, "completion_tokens": 1, "reasoning_tokens": 162, "cached_tokens": 128, "total_tokens": 353, "cost_in_usd_ticks": 4136000, "reasoning_content_returned": true }, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models + GET /v1/language-models (2026-09-19) and one minimal POST (see live_usage_shape)" }, "sources": [ { "url": "https://docs.x.ai/developers/models", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/models/grok-build-0.1", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/pricing", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rate-limits", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/model-capabilities/text/reasoning", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rest-api-reference/inference/models", "retrieved_at": "2026-09-19" }, { "url": "https://api.x.ai/v1/language-models", "retrieved_at": "2026-09-19", "note": "live 2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-imagine-image", "display_name": "Grok Imagine Image (1.0)", "kind": "model", "aliases": [ "grok-imagine-image-2026-03-02" ], "snapshots": [ "grok-imagine-image" ], "family": "Imagine", "generation": "image", "description": "Text/image -> image generation and editing model (Imagine API).", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "release_date": "2026-01 (release notes January 2026: 'next-gen image generation'); created 2026-01-28 live", "created_at_live": "2026-01-28", "fingerprint_live": "fp_574cc24a75", "knowledge_cutoff": null, "context_window": 16000, "context_window_note": "max_prompt_length 16000 (live)", "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "capabilities": { "image_generation": true, "image_editing": true, "multi_image_editing": true, "batch_api": "supported in us-east-1, us-west-2", "quality_parameter": false, "resolution_parameter": false, "files_api_inputs_outputs": true, "streaming": false, "function_calling": false, "reasoning": false }, "endpoints": [ "POST /v1/images/generations", "POST /v1/images/edits", "Batch API", "gRPC xai_api.Image/GenerateImage" ], "tools": [], "pricing": { "unit": "USD per image", "per_image_default": 0.02, "matrix": null, "batch_discount": 0.0, "note": "Batch API accepted (where supported) but billed at standard rates; also billable via the image_generation server-side tool" }, "rate_limits": { "documented": { "tier_rps_T0_T4": [ 6, 12, 25, 50, 100 ], "tpm": null, "note": "Imagine limits are not spend-tiered like text; contact sales@x.ai for increases" } }, "beta_headers": [], "restrictions": [ "not affected by the Nov 2 retirement of grok-imagine-image-quality" ], "availability": { "account": "available", "regions": [ "us-east-1", "us-west-2", "us-saltlake-2" ], "base_urls": [ "https://api.x.ai/v1 (not served on us.api.x.ai)" ] }, "deprecation": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models + GET /v1/image-generation-models; no image generated (cost)" }, "sources": [ { "url": "https://docs.x.ai/developers/models", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/models/grok-imagine-image", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/pricing", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rate-limits", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/model-capabilities/images/generation", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-imagine-image-2.0", "display_name": "Grok Imagine Image 2.0", "kind": "model", "aliases": [], "snapshots": [ "grok-imagine-image-2.0" ], "family": "Imagine", "generation": "image", "description": "Text/image -> image generation and editing model (Imagine API).", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "release_date": "2026-08 (release notes August 2026); created 2026-08-08 live", "created_at_live": "2026-08-08", "fingerprint_live": "fp_e15b3a1fcc", "knowledge_cutoff": null, "context_window": 64000, "context_window_note": "max_prompt_length 64000 (live)", "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "capabilities": { "image_generation": true, "image_editing": true, "multi_image_editing": true, "batch_api": "supported", "quality_parameter": true, "resolution_parameter": true, "files_api_inputs_outputs": true, "streaming": false, "function_calling": false, "reasoning": false }, "endpoints": [ "POST /v1/images/generations", "POST /v1/images/edits", "Batch API", "gRPC xai_api.Image/GenerateImage" ], "tools": [], "pricing": { "unit": "USD per image", "per_image_default": 0.06, "matrix": [ { "quality": "low", "resolution": "1k", "price": 0.04 }, { "quality": "low", "resolution": "2k", "price": 0.06 }, { "quality": "low", "resolution": "1.5k", "price": 0.05 }, { "quality": "medium", "resolution": "1k", "price": 0.06 }, { "quality": "medium", "resolution": "2k", "price": 0.08 }, { "quality": "medium", "resolution": "1.5k", "price": 0.07 } ], "batch_discount": 0.0, "note": "Batch API accepted (where supported) but billed at standard rates; also billable via the image_generation server-side tool" }, "rate_limits": { "documented": { "tier_rps_T0_T4": [ 6, 12, 25, 50, 100 ], "tpm": null, "note": "Imagine limits are not spend-tiered like text; contact sales@x.ai for increases" } }, "beta_headers": [], "restrictions": [ "quality: low | medium | auto (default since Aug 2026; auto = low for generation, medium for editing; billed at the quality served)", "resolution: 1k (default) | 1.5k | 2k", "up to 5 source images for editing; aspect ratios incl. 21:9 and 5:2", "recommended image model" ], "availability": { "account": "available", "regions": [ "us-east-1", "us-west-2" ], "base_urls": [ "https://api.x.ai/v1 (not served on us.api.x.ai)" ] }, "deprecation": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models + GET /v1/image-generation-models; no image generated (cost)" }, "sources": [ { "url": "https://docs.x.ai/developers/models", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/models/grok-imagine-image-2.0", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/pricing", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rate-limits", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/model-capabilities/images/generation", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-imagine-image-quality", "display_name": "Grok Imagine Image Quality", "kind": "model", "aliases": [ "grok-imagine-image-quality-20260403", "grok-imagine-image-quality-latest", "grok-imagine-image-pro" ], "snapshots": [ "grok-imagine-image-quality" ], "family": "Imagine", "generation": "image", "description": "Text/image -> image generation and editing model (Imagine API).", "status": [ "DOCUMENTED", "DEPRECATED", "LIVE_VERIFIED" ], "release_date": "2026-04-03 (alias grok-imagine-image-quality-20260403); created 2026-04-03 live", "created_at_live": "2026-04-03", "fingerprint_live": "fp_0515dcf784", "knowledge_cutoff": null, "context_window": 16000, "context_window_note": "max_prompt_length 16000 (live)", "max_output": null, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "capabilities": { "image_generation": true, "image_editing": true, "multi_image_editing": true, "batch_api": "not supported", "quality_parameter": false, "resolution_parameter": false, "files_api_inputs_outputs": true, "streaming": false, "function_calling": false, "reasoning": false }, "endpoints": [ "POST /v1/images/generations", "POST /v1/images/edits", "Batch API", "gRPC xai_api.Image/GenerateImage" ], "tools": [], "pricing": { "unit": "USD per image", "per_image_default": 0.05, "matrix": null, "batch_discount": 0.0, "note": "Batch API accepted (where supported) but billed at standard rates; also billable via the image_generation server-side tool" }, "rate_limits": { "documented": { "tier_rps_T0_T4": [ 6, 12, 25, 50, 100 ], "tpm": null, "note": "Imagine limits are not spend-tiered like text; contact sales@x.ai for increases" } }, "beta_headers": [], "restrictions": [ "RETIRES 2026-11-02: requests then served by grok-imagine-image-2.0 with quality=low ($0.01/image cheaper); slug keeps resolving", "grok-imagine-image-pro already redirects here (since 2026-05-15)" ], "availability": { "account": "available", "regions": [ "us-east-1", "us-west-2" ], "base_urls": [ "https://api.x.ai/v1 (not served on us.api.x.ai)" ] }, "deprecation": { "retirement": "2026-11-02", "replacement": "grok-imagine-image-2.0 (quality=low)" }, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models + GET /v1/image-generation-models; no image generated (cost)" }, "sources": [ { "url": "https://docs.x.ai/developers/models", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/models/grok-imagine-image-quality", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/pricing", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rate-limits", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/model-capabilities/images/generation", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-imagine-video", "display_name": "Grok Imagine Video (1.0)", "kind": "model", "aliases": [], "snapshots": [ "grok-imagine-video" ], "family": "Imagine", "generation": "video", "description": "Video generation / image-to-video / editing / extension model (Imagine API, asynchronous requests).", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "release_date": "2026-01 (release notes January 2026); created 2026-01-28 live", "created_at_live": "2026-01-28", "fingerprint_live": "fp_5f37b474c6", "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "video" ] }, "capabilities": { "text_to_video": true, "image_to_video": true, "video_editing": true, "video_extension": true, "reference_to_video": false, "batch_api": "supported in us-east-1, us-west-2", "files_api_inputs_outputs": true, "async_polling": true, "streaming": false, "reasoning": false }, "endpoints": [ "POST /v1/videos/generations", "POST /v1/videos/edits", "POST /v1/videos/extensions", "GET /v1/videos/{request_id}", "Batch API", "gRPC xai_api.Video/{GenerateVideo,ExtendVideo,GetDeferredVideo}" ], "tools": [], "pricing": { "unit": "USD per second of generated video", "per_second": 0.05, "batch_discount": 0.0, "note": "video URLs in batch results expire after 1 hour" }, "rate_limits": { "documented": { "tier_rps_T0_T4": [ 10, 20, 39, 79, 158 ], "tpm": null } }, "beta_headers": [], "restrictions": [ "input modalities live: text, image, video (video editing/extension)" ], "availability": { "account": "available", "regions": [ "us-east-1", "us-west-2", "us-saltlake-2" ], "base_urls": [ "https://api.x.ai/v1 (not served on us.api.x.ai)" ] }, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models + GET /v1/video-generation-models(/{id}); no video generated (cost)" }, "sources": [ { "url": "https://docs.x.ai/developers/models", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/models/grok-imagine-video", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/pricing", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rate-limits", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/model-capabilities/video/generation", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-imagine-video-1.5", "display_name": "Grok Imagine Video 1.5", "kind": "model", "aliases": [ "grok-imagine-video-1.5-preview", "grok-imagine-video-1.5-2026-05-30" ], "snapshots": [ "grok-imagine-video-1.5" ], "family": "Imagine", "generation": "video", "description": "Video generation / image-to-video / editing / extension model (Imagine API, asynchronous requests).", "status": [ "DOCUMENTED", "LIVE_VERIFIED" ], "release_date": "2026-05-30 (alias date; created 2026-05-27 live; July 2026 release notes for T2V/I2V/reference-to-video)", "created_at_live": "2026-05-27", "fingerprint_live": "fp_1f44669f1a", "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "video" ] }, "capabilities": { "text_to_video": true, "image_to_video": true, "video_editing": false, "video_extension": true, "reference_to_video": true, "batch_api": "supported", "files_api_inputs_outputs": true, "async_polling": true, "streaming": false, "reasoning": false }, "endpoints": [ "POST /v1/videos/generations", "POST /v1/videos/edits", "POST /v1/videos/extensions", "GET /v1/videos/{request_id}", "Batch API", "gRPC xai_api.Video/{GenerateVideo,ExtendVideo,GetDeferredVideo}" ], "tools": [], "pricing": { "unit": "USD per second of generated video", "per_second": 0.08, "batch_discount": 0.0, "note": "video URLs in batch results expire after 1 hour" }, "rate_limits": { "documented": { "tier_rps_T0_T4": [ 10, 20, 39, 79, 158 ], "tpm": null } }, "beta_headers": [], "restrictions": [ "text-to-video runs as text-to-image then image-to-video under the hood", "native 1080p for T2V and I2V; reference-to-video with optional preset voices", "live input_modalities include 'audio' (reference audio) while the model page lists text, image only" ], "availability": { "account": "available", "regions": [ "us-east-1", "us-west-2" ], "base_urls": [ "https://api.x.ai/v1 (not served on us.api.x.ai)" ] }, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models + GET /v1/video-generation-models(/{id}); no video generated (cost)" }, "sources": [ { "url": "https://docs.x.ai/developers/models", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/models/grok-imagine-video-1.5", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/pricing", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rate-limits", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/model-capabilities/video/generation", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "family": "Voice", "kind": "model", "snapshots": [], "knowledge_cutoff": null, "context_window": null, "max_output": null, "beta_headers": [], "last_verified": "2026-09-18", "id": "grok-voice-think-fast-2.0", "display_name": "Grok Voice Think Fast 2.0", "aliases": [ "grok-voice-latest (routes here since 2026-08-05)" ], "generation": "2.0", "description": "Speech-to-speech realtime voice model (WebSocket wss://api.x.ai/v1/realtime, OpenAI Realtime-compatible event protocol, SIP, ephemeral client secrets).", "status": [ "DOCUMENTED" ], "release_date": "2026-07 (release notes July 2026)", "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ] }, "capabilities": { "speech_to_speech": true, "function_calling": true, "web_search": true, "x_search": true, "collections_search": true, "remote_mcp": true, "custom_voices": true, "sip": true, "max_session_minutes": 120, "reasoning": "think-fast (built-in)" }, "endpoints": [ "WS wss://api.x.ai/v1/realtime?model=grok-voice-latest", "POST /v1/realtime/client_secrets", "/v1/realtime/calls/* (SIP)" ], "tools": [ "function", "web_search", "x_search", "collections_search", "mcp" ], "pricing": { "audio_per_minute": 0.08, "audio_per_hour": 4.8, "text_input_per_message": 0.004, "unit": "USD", "note": "audio sent or received billed per minute; each conversation.item.create text item billed $0.004 except function_call_output and audio items" }, "rate_limits": { "documented": { "concurrent_sessions_T0_T4": [ 10, 20, 50, 100, 200 ], "rps": null } }, "restrictions": [ "not in GET /v1/models (GET /v1/models/grok-voice-think-fast-2.0 -> 404 not-found live)", "not served on us.api.x.ai" ], "availability": { "regions": [ "us-east-1 (speech-to-speech page)", "model page: us-east-1, eu-west-1, us-saltlake-2" ], "account": "unknown (not exercised)" }, "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": "not_tested", "http_status": 404, "request_note": "GET /v1/models/grok-voice-think-fast-2.0 -> 404 (voice models are not in the models catalogue); realtime session not opened by this agent" }, "sources": [ { "url": "https://docs.x.ai/developers/models", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/models/speech-to-speech", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/models/grok-voice-think-fast-2.0", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/pricing", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rate-limits", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/model-capabilities/audio/speech-to-speech", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "family": "Voice", "kind": "model", "snapshots": [], "knowledge_cutoff": null, "context_window": null, "max_output": null, "beta_headers": [], "last_verified": "2026-09-18", "id": "grok-voice-think-fast-1.0", "display_name": "Grok Voice Think Fast 1.0", "aliases": [], "generation": "1.0", "description": "Previous speech-to-speech model (April 2026); grok-voice-latest moved to 2.0 on 2026-08-05.", "status": [ "DOCUMENTED", "LEGACY" ], "release_date": "2026-04 (release notes April 2026)", "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ] }, "capabilities": { "speech_to_speech": true }, "endpoints": [ "WS wss://api.x.ai/v1/realtime" ], "tools": [], "pricing": "not listed on the pricing page (only grok-voice-think-fast-2.0 is priced)", "rate_limits": null, "restrictions": [ "no retirement date documented" ], "availability": { "account": "unknown" }, "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": "not_tested", "http_status": null, "request_note": "release notes only" }, "sources": [ { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "family": "Voice", "kind": "model", "snapshots": [], "knowledge_cutoff": null, "context_window": null, "max_output": null, "beta_headers": [], "last_verified": "2026-09-18", "id": "grok-voice-transcribe-2.0", "display_name": "Grok Voice Transcribe 2.0", "aliases": [], "generation": "2.0", "description": "Speech-to-text model (REST POST /v1/stt and streaming wss://api.x.ai/v1/stt).", "status": [ "DOCUMENTED" ], "release_date": "2026-09 (release notes September 2026)", "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "speech_to_text": true, "streaming": true, "languages": "25 (STT GA note)", "smart_turn": true, "vad_threshold": true, "keyterm_prompting": true, "formats": [ "WAV", "MP3", "WebM", "OGG", "M4A" ] }, "endpoints": [ "POST /v1/stt", "WS wss://api.x.ai/v1/stt" ], "tools": [], "pricing": { "rest_per_hour": 0.1, "streaming_per_hour": 0.2, "unit": "USD per hour of audio" }, "rate_limits": { "documented": { "rps_T0_T4": [ 10, 10, 20, 30, 40 ], "concurrent_sessions_T0_T4": [ 100, 200, 200, 300, 500 ] } }, "restrictions": [ "DEFAULT DISCREPANCY: release notes say the default is grok-voice-transcribe-1.0; the Speech to Text model page says the default is grok-voice-transcribe-2.0" ], "availability": { "regions": [ "us-east-1" ] }, "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": "not_tested", "http_status": null, "request_note": "voice agent covers /v1/stt" }, "sources": [ { "url": "https://docs.x.ai/developers/models/speech-to-text", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/pricing", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rate-limits", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/model-capabilities/audio/speech-to-text", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "family": "Voice", "kind": "model", "snapshots": [], "knowledge_cutoff": null, "context_window": null, "max_output": null, "beta_headers": [], "last_verified": "2026-09-18", "id": "grok-voice-transcribe-1.0", "display_name": "Grok Voice Transcribe 1.0", "aliases": [], "generation": "1.0", "description": "First speech-to-text model (STT GA April 2026).", "status": [ "DOCUMENTED" ], "release_date": "2026-04 (STT GA)", "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "speech_to_text": true, "streaming": true }, "endpoints": [ "POST /v1/stt", "WS wss://api.x.ai/v1/stt" ], "tools": [], "pricing": { "rest_per_hour": 0.1, "streaming_per_hour": 0.2, "unit": "USD per hour of audio" }, "rate_limits": "same table as Speech to Text", "restrictions": [], "availability": { "regions": [ "us-east-1" ] }, "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": "not_tested", "http_status": null, "request_note": null }, "sources": [ { "url": "https://docs.x.ai/developers/models/speech-to-text", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "family": "Voice", "kind": "service", "snapshots": [], "knowledge_cutoff": null, "context_window": null, "max_output": null, "beta_headers": [], "last_verified": "2026-09-18", "id": "text-to-speech", "display_name": "Grok Text to Speech (service, no model id documented)", "aliases": [], "generation": null, "description": "Text-to-speech API (POST /v1/tts, streaming wss://api.x.ai/v1/tts, voice catalogue GET /v1/tts/voices, custom voices). Docs do not expose a model id; requests select a voice.", "status": [ "DOCUMENTED" ], "release_date": "2026-03 (release notes March 2026)", "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "text_to_speech": true, "streaming": true, "custom_voices": true, "formats": [ "MP3", "WAV", "PCM", "mu-law", "A-law" ] }, "endpoints": [ "POST /v1/tts", "WS wss://api.x.ai/v1/tts", "GET /v1/tts/voices", "GET /v1/tts/voices/{voice}" ], "tools": [], "pricing": { "per_1M_characters": 15.0, "unit": "USD per 1M input characters" }, "rate_limits": { "documented": { "rps_T0_T4": [ 50, 50, 100, 250, 500 ], "concurrent_sessions_T0_T4": [ 100, 200, 200, 300, 500 ] } }, "restrictions": [], "availability": { "regions": [ "us-east-1" ] }, "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": "not_tested", "http_status": null, "request_note": "voice agent covers /v1/tts" }, "sources": [ { "url": "https://docs.x.ai/developers/models/text-to-speech", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/pricing", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rate-limits", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/model-capabilities/audio/text-to-speech", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-embedding-small", "display_name": "Grok Embedding Small", "kind": "model", "aliases": [], "snapshots": [], "family": "Embeddings", "generation": null, "description": "Embedding model referenced as Collections index_configuration.model_name in the Collections API reference. /v1/embedding-models exists (OpenAPI + live) and returns an empty list for our team.", "status": [ "DOCUMENTED", "ACCOUNT_RESTRICTED" ], "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "capabilities": { "embeddings": true, "collections_indexing": true }, "endpoints": [ "POST /v1/embeddings (OpenAPI)", "GET /v1/embedding-models(/{id})", "gRPC xai_api.Embedder/Embed" ], "tools": [], "pricing": "not on the pricing page; EmbeddingModel schema carries prompt_text_token_price / prompt_image_token_price", "rate_limits": "rate-limit tiers apply to embedding models (rate-limits page); no table published", "beta_headers": [], "restrictions": [ "GET /v1/embedding-models -> {\"models\": []} and GET /v1/embedding-models/grok-embedding-small -> 404 not-found ('does not exist or your team ... does not have access') with our key" ], "availability": { "account": "not available to our team" }, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "restricted", "http_status": 404, "request_note": "GET /v1/embedding-models (200, empty) + GET /v1/embedding-models/grok-embedding-small (404)" }, "sources": [ { "url": "https://docs.x.ai/developers/rest-api-reference/collections/collection", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rest-api-reference/inference/models", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/rate-limits", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-3", "display_name": "Grok 3", "kind": "retired_redirect", "aliases": [], "snapshots": [], "family": "Grok 3", "status": [ "DOCUMENTED", "RETIRED" ], "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [], "output": [] }, "capabilities": {}, "endpoints": [], "tools": [], "pricing": null, "rate_limits": null, "beta_headers": [], "deprecation": { "retirement": "2026-05-15T12:00 PT", "replacement": "grok-4.3 (reasoning_effort none)", "note": "billed at grok-4.3 rates after redirect" }, "restrictions": [], "availability": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models/grok-3 -> 200 with id 'grok-4.3' (redirect confirmed live 2026-09-19)" }, "sources": [ { "url": "https://docs.x.ai/developers/migration/may-15-retirement", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-4-0709", "display_name": "Grok 4 (0709)", "kind": "retired_redirect", "aliases": [], "snapshots": [], "family": "Grok 4", "status": [ "DOCUMENTED", "RETIRED" ], "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [], "output": [] }, "capabilities": {}, "endpoints": [], "tools": [], "pricing": null, "rate_limits": null, "beta_headers": [], "deprecation": { "retirement": "2026-05-15T12:00 PT", "replacement": "grok-4.3 (reasoning_effort low)", "note": "Grok 4 launched July 2025" }, "restrictions": [], "availability": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/language-models/grok-4-0709 -> 200 with id 'grok-4.3' (redirect confirmed live 2026-09-19)" }, "sources": [ { "url": "https://docs.x.ai/developers/migration/may-15-retirement", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-4-fast-reasoning", "display_name": "Grok 4 Fast (reasoning)", "kind": "retired_redirect", "aliases": [ "grok-4-fast (probed)" ], "snapshots": [], "family": "Grok 4", "status": [ "DOCUMENTED", "RETIRED" ], "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [], "output": [] }, "capabilities": {}, "endpoints": [], "tools": [], "pricing": null, "rate_limits": null, "beta_headers": [], "deprecation": { "retirement": "2026-05-15T12:00 PT", "replacement": "grok-4.3 (reasoning_effort low)", "note": "slug keeps resolving" }, "restrictions": [], "availability": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models/grok-4-fast -> 200 with id 'grok-4.3' (redirect confirmed live 2026-09-19)" }, "sources": [ { "url": "https://docs.x.ai/developers/migration/may-15-retirement", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-4-fast-non-reasoning", "display_name": "Grok 4 Fast (non-reasoning)", "kind": "retired_redirect", "aliases": [], "snapshots": [], "family": "Grok 4", "status": [ "DOCUMENTED", "RETIRED" ], "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [], "output": [] }, "capabilities": {}, "endpoints": [], "tools": [], "pricing": null, "rate_limits": null, "beta_headers": [], "deprecation": { "retirement": "2026-05-15T12:00 PT", "replacement": "grok-4.3 (reasoning_effort none)", "note": "slug keeps resolving" }, "restrictions": [], "availability": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": "not_tested", "http_status": null, "request_note": "not probed" }, "sources": [ { "url": "https://docs.x.ai/developers/migration/may-15-retirement", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-4-1-fast-reasoning", "display_name": "Grok 4.1 Fast (reasoning)", "kind": "retired_redirect", "aliases": [], "snapshots": [], "family": "Grok 4.1", "status": [ "DOCUMENTED", "RETIRED" ], "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [], "output": [] }, "capabilities": {}, "endpoints": [], "tools": [], "pricing": null, "rate_limits": null, "beta_headers": [], "deprecation": { "retirement": "2026-05-15T12:00 PT", "replacement": "grok-4.3 (reasoning_effort low)", "note": "launched Nov 2025 (Enterprise API)" }, "restrictions": [], "availability": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": "not_tested", "http_status": null, "request_note": "not probed" }, "sources": [ { "url": "https://docs.x.ai/developers/migration/may-15-retirement", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-4-1-fast-non-reasoning", "display_name": "Grok 4.1 Fast (non-reasoning)", "kind": "retired_redirect", "aliases": [], "snapshots": [], "family": "Grok 4.1", "status": [ "DOCUMENTED", "RETIRED" ], "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [], "output": [] }, "capabilities": {}, "endpoints": [], "tools": [], "pricing": null, "rate_limits": null, "beta_headers": [], "deprecation": { "retirement": "2026-05-15T12:00 PT", "replacement": "grok-4.3 (reasoning_effort none)", "note": null }, "restrictions": [], "availability": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": "not_tested", "http_status": null, "request_note": "not probed" }, "sources": [ { "url": "https://docs.x.ai/developers/migration/may-15-retirement", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-code-fast-1", "display_name": "Grok Code Fast 1", "kind": "alias", "aliases": [], "snapshots": [], "family": "Build", "status": [ "DOCUMENTED", "RETIRED" ], "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [], "output": [] }, "capabilities": {}, "endpoints": [], "tools": [], "pricing": null, "rate_limits": null, "beta_headers": [], "deprecation": { "retirement": "2026-05-15T12:00 PT", "replacement": "grok-build-0.1", "note": "now listed as an alias of grok-build-0.1 in the live catalogue (with grok-code-fast, grok-code-fast-1-0825)" }, "restrictions": [], "availability": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "GET /v1/models/grok-code-fast-1 -> 200 with id 'grok-build-0.1' (redirect confirmed live 2026-09-19)" }, "sources": [ { "url": "https://docs.x.ai/developers/migration/may-15-retirement", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/models/grok-build-0.1", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-imagine-image-pro", "display_name": "Grok Imagine Image Pro", "kind": "alias", "aliases": [], "snapshots": [], "family": "Imagine", "status": [ "DOCUMENTED", "RETIRED" ], "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [], "output": [] }, "capabilities": {}, "endpoints": [], "tools": [], "pricing": null, "rate_limits": null, "beta_headers": [], "deprecation": { "retirement": "2026-05-15T12:00 PT", "replacement": "grok-imagine-image-quality (then grok-imagine-image-2.0 quality=low from 2026-11-02)", "note": "alias of grok-imagine-image-quality in the live catalogue" }, "restrictions": [], "availability": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "success", "http_status": 200, "request_note": "appears in aliases of grok-imagine-image-quality (GET /v1/models)" }, "sources": [ { "url": "https://docs.x.ai/developers/migration/may-15-retirement", "retrieved_at": "2026-09-19" }, { "url": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-2-image-1212", "display_name": "Grok 2 Image", "kind": "legacy", "aliases": [], "snapshots": [], "family": "Grok 2", "status": [ "LEGACY", "UNVERIFIED" ], "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [], "output": [] }, "capabilities": {}, "endpoints": [], "tools": [], "pricing": null, "rate_limits": null, "beta_headers": [], "deprecation": { "retirement": "not documented", "replacement": null, "note": "image generation model of March 2025; GET /v1/models/grok-2-image -> 404 not-found (2026-09-19)" }, "restrictions": [], "availability": null, "last_verified": "2026-09-18", "verification": { "method": "live_api", "verified_at": "2026-09-18", "result": "failure", "http_status": 404, "request_note": "GET /v1/models/grok-2-image -> 404 {code: not-found}; POST /v1/chat/completions model=grok-2-image -> 404" }, "sources": [ { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-2-vision-1212", "display_name": "Grok 2 Vision", "kind": "legacy", "aliases": [], "snapshots": [], "family": "Grok 2", "status": [ "LEGACY", "UNVERIFIED" ], "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [], "output": [] }, "capabilities": {}, "endpoints": [], "tools": [], "pricing": null, "rate_limits": null, "beta_headers": [], "deprecation": { "retirement": "not documented", "replacement": null, "note": "released December 2024" }, "restrictions": [], "availability": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": "not_tested", "http_status": null, "request_note": "mentioned only in release notes / legacy reference examples; absent from current models & pricing pages" }, "sources": [ { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-2-1212", "display_name": "Grok 2", "kind": "legacy", "aliases": [], "snapshots": [], "family": "Grok 2", "status": [ "LEGACY", "UNVERIFIED" ], "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [], "output": [] }, "capabilities": {}, "endpoints": [], "tools": [], "pricing": null, "rate_limits": null, "beta_headers": [], "deprecation": { "retirement": "not documented", "replacement": null, "note": "released December 2024" }, "restrictions": [], "availability": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": "not_tested", "http_status": null, "request_note": "mentioned only in release notes / legacy reference examples; absent from current models & pricing pages" }, "sources": [ { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-3-mini", "display_name": "Grok 3 Mini", "kind": "legacy", "aliases": [], "snapshots": [], "family": "Grok 3", "status": [ "LEGACY", "UNVERIFIED" ], "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [], "output": [] }, "capabilities": {}, "endpoints": [], "tools": [], "pricing": null, "rate_limits": null, "beta_headers": [], "deprecation": { "retirement": "not documented", "replacement": null, "note": "grok-3-mini / -fast / -latest / -beta appear in legacy examples only" }, "restrictions": [], "availability": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": "not_tested", "http_status": null, "request_note": "mentioned only in release notes / legacy reference examples; absent from current models & pricing pages" }, "sources": [ { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-beta", "display_name": "Grok beta", "kind": "legacy", "aliases": [], "snapshots": [], "family": "Grok 1/beta", "status": [ "LEGACY", "UNVERIFIED" ], "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [], "output": [] }, "capabilities": {}, "endpoints": [], "tools": [], "pricing": null, "rate_limits": null, "beta_headers": [], "deprecation": { "retirement": "not documented", "replacement": null, "note": "public beta November 2024" }, "restrictions": [], "availability": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": "not_tested", "http_status": null, "request_note": "mentioned only in release notes / legacy reference examples; absent from current models & pricing pages" }, "sources": [ { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-vision-beta", "display_name": "Grok Vision beta", "kind": "legacy", "aliases": [], "snapshots": [], "family": "Grok 1/beta", "status": [ "LEGACY", "UNVERIFIED" ], "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [], "output": [] }, "capabilities": {}, "endpoints": [], "tools": [], "pricing": null, "rate_limits": null, "beta_headers": [], "deprecation": { "retirement": "not documented", "replacement": null, "note": "public beta November 2024" }, "restrictions": [], "availability": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": "not_tested", "http_status": null, "request_note": "mentioned only in release notes / legacy reference examples; absent from current models & pricing pages" }, "sources": [ { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" }, { "provider": "xai", "id": "grok-4-latest", "display_name": "grok-4 / grok-4-latest", "kind": "legacy", "aliases": [], "snapshots": [], "family": "Grok 4", "status": [ "LEGACY", "UNVERIFIED" ], "release_date": null, "knowledge_cutoff": null, "context_window": null, "max_output": null, "modalities": { "input": [], "output": [] }, "capabilities": {}, "endpoints": [], "tools": [], "pricing": null, "rate_limits": null, "beta_headers": [], "deprecation": { "retirement": "not documented", "replacement": null, "note": "alias family of Grok 4 (July 2025); grok-4-0709 retired 2026-05-15" }, "restrictions": [], "availability": null, "last_verified": "2026-09-18", "verification": { "method": "docs_only", "verified_at": "2026-09-18", "result": "not_tested", "http_status": null, "request_note": "mentioned only in release notes / legacy reference examples; absent from current models & pricing pages" }, "sources": [ { "url": "https://docs.x.ai/developers/release-notes", "retrieved_at": "2026-09-19" } ], "_fragment": "generated/fragments/models/xai-models.json" } ]