{ "record_type": "model", "provider": "gemini", "generated_at": "2026-09-18", "generator": "scripts/gen_gemini_models_fragment.py", "live_listing": { "v1beta_count": 58, "v1_count": 22, "retrieved_at": "2026-09-19" }, "count": 97, "records": [ { "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" }, { "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" }, { "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" }, { "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" }, { "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" ] } }, { "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" } ] }, { "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" ] } }, { "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)" }, { "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" } ] } } } }, { "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" } } } }, { "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" }, { "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" }, { "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" } ] } } } }, { "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" }, { "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" }, { "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" }, { "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" }, { "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" }, { "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" }, { "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" }, { "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" }, { "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" }, { "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" ] } }, { "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" ] } }, { "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" }, { "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" }, { "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" }, { "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" }, { "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" }, { "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" ] } }, { "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" }, { "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" }, { "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" }, { "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" }, { "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" }, { "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" }, { "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" }, { "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" } ] }, { "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" }, { "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" }, { "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" }, { "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" }, { "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" }, { "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" }, { "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" } ] }, { "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" }, { "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" }, { "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" }, { "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" }, { "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)" }, { "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" } ] }, { "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" }, { "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" }, { "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" }, { "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" }, { "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" }, { "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" }, { "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" }, { "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" }, { "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" } ] }, { "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" }, { "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" } ] }, { "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" } ] }, { "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" } ] }, { "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" } ] }, { "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" } ] }, { "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" } ] }, { "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" } ] }, { "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" } ] }, { "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" } ] }, { "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" } ] }, { "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" }, { "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" } ] }, { "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" }, { "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" } ] }, { "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" } ] }, { "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" } ] }, { "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" } ] }, { "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" } ] }, { "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" } ] }, { "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" } ] }, { "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" } ] }, { "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" }, { "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" }, { "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" }, { "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" } ] }, { "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" } ] }, { "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" } ] }, { "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" }, { "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" } ] }, { "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" } ] }, { "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" } ] }, { "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" } ] }, { "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" }, { "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" }, { "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" }, { "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" } ] }