Python 88.3%
TypeScript 7.6%
Shell 4.1%
1provider,type,name,category,status,compatible_models,compatible_endpoints,beta_header,billing,verification_result,source2anthropic,custom,Custom (user-defined) client tool,client,DOCUMENTED|LIVE_VERIFIED,claude-fable-5-1|claude-opus-5|claude-sonnet-5|claude-fable-5|claude-opus-4-8|claude-opus-4-7|claude-sonnet-4-6|claude-opus-4-6|claude-opus-4-5-20251101|claude-haiku-4-5-20251001|claude-sonnet-4-5-20250929|claude-mythos-5-1|claude-mythos-5,POST /v1/messages|POST /v1/messages/batches,,"Tokens only. Tool-use system prompt overhead per model (auto/none vs any/tool): {""claude-opus-5"": [286, 406], ""claude-opus-4-8"": [290, 410], ""claude-opus-4-7"": [675, 804], ""claude-opus-4-6"": [497, 589], ""claude-opus-4-5-20251101"": [496, 588], ""claude-sonnet-5"": [354, 474], ""claude-sonnet-4-6"": [497, 589], ""claude-sonnet-4-5-20250929"": [496, 588], ""claude-haiku-4-5-20251001"": [496, 588]}. Live count_tokens on haiku 4.5: 11 tokens without tools, 581 with one small get_weather tool (auto), 673 with tool_choice any (+92). input_examples add ~20-200 tokens each.",success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/define-tools|https://platform.claude.com/docs/en/agents-and-tools/tool-use/handle-tool-calls|https://platform.claude.com/docs/en/agents-and-tools/tool-use/parallel-tool-use|https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use|https://platform.claude.com/docs/en/agents-and-tools/tool-use/fine-grained-tool-streaming|https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview|https://platform.claude.com/docs/en/api/messages/create3anthropic,bash_20250124,Bash tool,anthropic-defined-client,DOCUMENTED|LIVE_VERIFIED,claude-fable-5-1|claude-opus-5|claude-sonnet-5|claude-fable-5|claude-opus-4-8|claude-opus-4-7|claude-sonnet-4-6|claude-opus-4-6|claude-opus-4-5-20251101|claude-haiku-4-5-20251001|claude-sonnet-4-5-20250929|claude-mythos-5-1|claude-mythos-5,POST /v1/messages|POST /v1/messages/batches,,"Definition adds ~325 input tokens (Opus 5/4.8/4.7) or ~244 (Opus 4.6, Sonnet 4.6 and earlier) + tool-use system prompt. Live count_tokens haiku 4.5: 751 tokens total for one short message + bash tool (vs 11 without tools).",success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/bash-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/api/messages/create4anthropic,text_editor_20250728,Text editor tool (text_editor_20250728),anthropic-defined-client,DOCUMENTED|LIVE_VERIFIED,claude-fable-5-1|claude-opus-5|claude-sonnet-5|claude-fable-5|claude-opus-4-8|claude-opus-4-7|claude-sonnet-4-6|claude-opus-4-6|claude-opus-4-5-20251101|claude-haiku-4-5-20251001|claude-sonnet-4-5-20250929|claude-mythos-5-1|claude-mythos-5,POST /v1/messages|POST /v1/messages/batches,,~700 additional input tokens for the definition (docs figure for text_editor_20250429 on Claude 4.x). Live count_tokens haiku 4.5 with text_editor_20250728: 1252 tokens (vs 11 without tools).,success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/text-editor-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/api/messages/create5anthropic,text_editor_20250429,Text editor tool (text_editor_20250429),anthropic-defined-client,DOCUMENTED|LEGACY,,POST /v1/messages|POST /v1/messages/batches,,~700 additional input tokens for the definition (docs figure for text_editor_20250429 on Claude 4.x). Live count_tokens haiku 4.5 with text_editor_20250728: 1252 tokens (vs 11 without tools).,failure,https://platform.claude.com/docs/en/agents-and-tools/tool-use/text-editor-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/api/messages/create6anthropic,text_editor_20250124,Text editor tool (text_editor_20250124),anthropic-defined-client,DOCUMENTED|LEGACY,,POST /v1/messages|POST /v1/messages/batches,,~700 additional input tokens for the definition (docs figure for text_editor_20250429 on Claude 4.x). Live count_tokens haiku 4.5 with text_editor_20250728: 1252 tokens (vs 11 without tools).,failure,https://platform.claude.com/docs/en/agents-and-tools/tool-use/text-editor-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/api/messages/create7anthropic,memory_20250818,Memory tool,anthropic-defined-client,DOCUMENTED|LIVE_VERIFIED,claude-fable-5-1|claude-opus-5|claude-sonnet-5|claude-fable-5|claude-opus-4-8|claude-opus-4-7|claude-sonnet-4-6|claude-opus-4-6|claude-opus-4-5-20251101|claude-haiku-4-5-20251001|claude-sonnet-4-5-20250929|claude-mythos-5-1|claude-mythos-5,POST /v1/messages|POST /v1/messages/batches,,Tokens only. Live count_tokens haiku 4.5: 1576 tokens with the memory tool (vs 11 without) — includes injected memory protocol.,success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference8anthropic,computer_toolset_20260801,Computer use toolset (GA),anthropic-defined-client,DOCUMENTED|LIVE_VERIFIED,claude-fable-5-1|claude-mythos-5-1|claude-fable-5|claude-mythos-5|claude-opus-5|claude-sonnet-5|claude-opus-4-8,POST /v1/messages|POST /v1/messages/batches,,"~4,500 input tokens for the toolset definition + tool-use system prompt (≈4,520 on Fable 5/Mythos 5/Opus 5/Opus 4.8, ≈4,590 on Sonnet 5; disabling zoom saves ≈410). Screenshots billed as image input (~1,000-1,800 tokens each).",success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/release-notes/api|https://platform.claude.com/docs/en/api/messages/create9anthropic,computer_20251124,"Computer use tool (beta, computer_20251124)",anthropic-defined-client,DOCUMENTED|BETA|LIVE_VERIFIED,claude-fable-5-1|claude-mythos-5-1|claude-fable-5|claude-mythos-5|claude-opus-5|claude-sonnet-5|claude-opus-4-8|claude-opus-4-7|claude-opus-4-6|claude-sonnet-4-6|claude-opus-4-5-20251101,POST /v1/messages|POST /v1/messages/batches,computer-use-2025-11-24,System prompt overhead 466-499 tokens + ~735 tokens per tool definition (measured with computer_20250124). Live sonnet 4.6: input_tokens 1843 for 'Take a screenshot.',success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool|https://platform.claude.com/docs/en/api/beta/messages/create|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference10anthropic,computer_20250124,"Computer use tool (beta, computer_20250124)",anthropic-defined-client,DOCUMENTED|BETA|LIVE_VERIFIED,claude-sonnet-4-5-20250929|claude-haiku-4-5-20251001,POST /v1/messages|POST /v1/messages/batches,computer-use-2025-01-24,~735 tokens per definition + 466-499 system prompt tokens (docs). Live count_tokens haiku 4.5: 1826 tokens for one short message + computer_20250124 (vs 11 without tools).,success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool|https://platform.claude.com/docs/en/api/beta/messages/create|https://platform.claude.com/docs/en/release-notes/api11anthropic,computer_20241022,"Computer use tool (legacy, computer_20241022)",anthropic-defined-client,DOCUMENTED|LEGACY|RETIRED,,POST /v1/messages|POST /v1/messages/batches,computer-use-2024-10-22,Standard input/output tokens (definition + tool_use + tool_result blocks) plus the per-model tool-use system prompt.,success,https://platform.claude.com/docs/en/release-notes/api|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference12anthropic,browser_toolset_20260801,Browser use toolset,anthropic-defined-client,DOCUMENTED|LIVE_VERIFIED,claude-fable-5-1|claude-mythos-5-1|claude-fable-5|claude-mythos-5|claude-opus-5|claude-sonnet-5|claude-opus-4-8,POST /v1/messages|POST /v1/messages/batches,,"Toolset definition ≈6,000+ input tokens (live 6689 total for a one-line prompt on Sonnet 5); screenshots as image input.",success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/release-notes/api|https://platform.claude.com/docs/en/api/messages/create13anthropic,web_search_20250305,Web search tool (web_search_20250305),server,DOCUMENTED|LIVE_VERIFIED,claude-fable-5-1|claude-opus-5|claude-sonnet-5|claude-fable-5|claude-opus-4-8|claude-opus-4-7|claude-sonnet-4-6|claude-opus-4-6|claude-opus-4-5-20251101|claude-haiku-4-5-20251001|claude-sonnet-4-5-20250929|claude-mythos-5-1|claude-mythos-5,POST /v1/messages|POST /v1/messages/batches,,"$10 per 1,000 searches (usage.server_tool_use.web_search_requests) + tokens for results in context (encrypted_content counts as input on later turns). Errors are not billed. Code execution used for dynamic filtering is free. Live c4: 10,491 input tokens for one search on haiku.",success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/api/messages/create|https://platform.claude.com/docs/en/release-notes/api14anthropic,web_search_20260209,Web search tool (web_search_20260209),server,DOCUMENTED|LIVE_VERIFIED,claude-fable-5-1|claude-opus-5|claude-sonnet-5|claude-fable-5|claude-opus-4-8|claude-opus-4-7|claude-sonnet-4-6|claude-opus-4-6|claude-opus-4-5-20251101|claude-haiku-4-5-20251001|claude-sonnet-4-5-20250929|claude-mythos-5-1|claude-mythos-5,POST /v1/messages|POST /v1/messages/batches,,"$10 per 1,000 searches (usage.server_tool_use.web_search_requests) + tokens for results in context (encrypted_content counts as input on later turns). Errors are not billed. Code execution used for dynamic filtering is free. Live c4: 10,491 input tokens for one search on haiku.",success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/api/messages/create|https://platform.claude.com/docs/en/release-notes/api15anthropic,web_search_20260318,Web search tool (web_search_20260318),server,DOCUMENTED,claude-fable-5-1|claude-opus-5|claude-sonnet-5|claude-fable-5|claude-opus-4-8|claude-opus-4-7|claude-sonnet-4-6|claude-opus-4-6|claude-opus-4-5-20251101|claude-haiku-4-5-20251001|claude-sonnet-4-5-20250929|claude-mythos-5-1|claude-mythos-5,POST /v1/messages|POST /v1/messages/batches,,"$10 per 1,000 searches (usage.server_tool_use.web_search_requests) + tokens for results in context (encrypted_content counts as input on later turns). Errors are not billed. Code execution used for dynamic filtering is free. Live c4: 10,491 input tokens for one search on haiku.",success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/api/messages/create|https://platform.claude.com/docs/en/release-notes/api16anthropic,web_fetch_20250910,Web fetch tool (web_fetch_20250910),server,DOCUMENTED|LIVE_VERIFIED,claude-fable-5-1|claude-opus-5|claude-sonnet-5|claude-fable-5|claude-opus-4-8|claude-opus-4-7|claude-sonnet-4-6|claude-opus-4-6|claude-opus-4-5-20251101|claude-haiku-4-5-20251001|claude-sonnet-4-5-20250929|claude-mythos-5-1|claude-mythos-5,POST /v1/messages|POST /v1/messages/batches,,"No per-call charge; tokens of fetched content only (~2,500 tokens per 10 kB page; 500 kB PDF ≈125k tokens). usage.server_tool_use.web_fetch_requests counts fetches. Live d1: 3,319 input tokens for example.com.",success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/api/messages/create17anthropic,web_fetch_20260209,Web fetch tool (web_fetch_20260209),server,DOCUMENTED,claude-fable-5-1|claude-opus-5|claude-sonnet-5|claude-fable-5|claude-opus-4-8|claude-opus-4-7|claude-sonnet-4-6|claude-opus-4-6|claude-opus-4-5-20251101|claude-haiku-4-5-20251001|claude-sonnet-4-5-20250929|claude-mythos-5-1|claude-mythos-5,POST /v1/messages|POST /v1/messages/batches,,"No per-call charge; tokens of fetched content only (~2,500 tokens per 10 kB page; 500 kB PDF ≈125k tokens). usage.server_tool_use.web_fetch_requests counts fetches. Live d1: 3,319 input tokens for example.com.",success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/api/messages/create18anthropic,web_fetch_20260309,Web fetch tool (web_fetch_20260309),server,DOCUMENTED,claude-fable-5-1|claude-opus-5|claude-sonnet-5|claude-fable-5|claude-opus-4-8|claude-opus-4-7|claude-sonnet-4-6|claude-opus-4-6|claude-opus-4-5-20251101|claude-haiku-4-5-20251001|claude-sonnet-4-5-20250929|claude-mythos-5-1|claude-mythos-5,POST /v1/messages|POST /v1/messages/batches,,"No per-call charge; tokens of fetched content only (~2,500 tokens per 10 kB page; 500 kB PDF ≈125k tokens). usage.server_tool_use.web_fetch_requests counts fetches. Live d1: 3,319 input tokens for example.com.",success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/api/messages/create19anthropic,web_fetch_20260318,Web fetch tool (web_fetch_20260318),server,DOCUMENTED|LIVE_VERIFIED,claude-fable-5-1|claude-opus-5|claude-sonnet-5|claude-fable-5|claude-opus-4-8|claude-opus-4-7|claude-sonnet-4-6|claude-opus-4-6|claude-opus-4-5-20251101|claude-haiku-4-5-20251001|claude-sonnet-4-5-20250929|claude-mythos-5-1|claude-mythos-5,POST /v1/messages|POST /v1/messages/batches,,"No per-call charge; tokens of fetched content only (~2,500 tokens per 10 kB page; 500 kB PDF ≈125k tokens). usage.server_tool_use.web_fetch_requests counts fetches. Live d1: 3,319 input tokens for example.com.",success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/api/messages/create20anthropic,code_execution_20250825,Code execution tool (code_execution_20250825),server,DOCUMENTED|LIVE_VERIFIED,claude-fable-5-1|claude-mythos-5-1|claude-fable-5|claude-mythos-5|claude-opus-5|claude-opus-4-8|claude-opus-4-7|claude-opus-4-6|claude-opus-4-5-20251101|claude-sonnet-5|claude-sonnet-4-6|claude-sonnet-4-5-20250929|claude-haiku-4-5-20251001,POST /v1/messages|POST /v1/messages/batches,,"Free when web_search_20260209+/web_fetch_20260209+ is in the request. Otherwise billed per container-hour: 5-minute minimum per session, 1,550 free hours/org/month, then $0.05/hour/container; files preloaded bill time even if the tool is not called. Tokens as usual (live e1: 4,611 input tokens on haiku for a one-line prompt).",success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling|https://platform.claude.com/docs/en/build-with-claude/skills-guide|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/api/messages/create|https://platform.claude.com/docs/en/release-notes/api21anthropic,code_execution_20260120,Code execution tool (code_execution_20260120),server,DOCUMENTED|LIVE_VERIFIED,claude-fable-5-1|claude-mythos-5-1|claude-fable-5|claude-mythos-5|claude-opus-5|claude-opus-4-8|claude-opus-4-7|claude-opus-4-6|claude-opus-4-5-20251101|claude-sonnet-5|claude-sonnet-4-6|claude-sonnet-4-5-20250929|claude-haiku-4-5-20251001,POST /v1/messages|POST /v1/messages/batches,,"Free when web_search_20260209+/web_fetch_20260209+ is in the request. Otherwise billed per container-hour: 5-minute minimum per session, 1,550 free hours/org/month, then $0.05/hour/container; files preloaded bill time even if the tool is not called. Tokens as usual (live e1: 4,611 input tokens on haiku for a one-line prompt).",success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling|https://platform.claude.com/docs/en/build-with-claude/skills-guide|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/api/messages/create|https://platform.claude.com/docs/en/release-notes/api22anthropic,code_execution_20260521,Code execution tool (code_execution_20260521),server,DOCUMENTED|LIVE_VERIFIED,claude-fable-5-1|claude-mythos-5-1|claude-fable-5|claude-mythos-5|claude-opus-5|claude-opus-4-8|claude-opus-4-7|claude-opus-4-6|claude-opus-4-5-20251101|claude-sonnet-5|claude-sonnet-4-6|claude-sonnet-4-5-20250929|claude-haiku-4-5-20251001,POST /v1/messages|POST /v1/messages/batches,,"Free when web_search_20260209+/web_fetch_20260209+ is in the request. Otherwise billed per container-hour: 5-minute minimum per session, 1,550 free hours/org/month, then $0.05/hour/container; files preloaded bill time even if the tool is not called. Tokens as usual (live e1: 4,611 input tokens on haiku for a one-line prompt).",success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling|https://platform.claude.com/docs/en/build-with-claude/skills-guide|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/api/messages/create|https://platform.claude.com/docs/en/release-notes/api23anthropic,code_execution_20250522,Code execution tool (code_execution_20250522),server,DOCUMENTED|LEGACY,claude-fable-5-1|claude-mythos-5-1|claude-fable-5|claude-mythos-5|claude-opus-5|claude-opus-4-8|claude-opus-4-7|claude-opus-4-6|claude-opus-4-5-20251101|claude-sonnet-5|claude-sonnet-4-6|claude-sonnet-4-5-20250929|claude-haiku-4-5-20251001,POST /v1/messages|POST /v1/messages/batches,,"Free when web_search_20260209+/web_fetch_20260209+ is in the request. Otherwise billed per container-hour: 5-minute minimum per session, 1,550 free hours/org/month, then $0.05/hour/container; files preloaded bill time even if the tool is not called. Tokens as usual (live e1: 4,611 input tokens on haiku for a one-line prompt).",success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling|https://platform.claude.com/docs/en/build-with-claude/skills-guide|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/api/messages/create|https://platform.claude.com/docs/en/release-notes/api24anthropic,tool_search_tool_regex_20251119,Tool search tool (tool_search_tool_regex),server,DOCUMENTED|LIVE_VERIFIED,claude-fable-5-1|claude-mythos-5-1|claude-fable-5|claude-mythos-5|claude-opus-5|claude-opus-4-8|claude-opus-4-7|claude-opus-4-6|claude-sonnet-4-6|claude-opus-4-5-20251101|claude-sonnet-4-5-20250929|claude-haiku-4-5-20251001,POST /v1/messages|POST /v1/messages/batches,,"Not metered as a server tool (no usage.server_tool_use field); loaded definitions count as input tokens. Live f1: 1,635 input tokens with 6 deferred tools + search tool (vs 581 for one plain tool).",success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-search-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-use-with-prompt-caching|https://platform.claude.com/docs/en/api/messages/create25anthropic,tool_search_tool_bm25_20251119,Tool search tool (tool_search_tool_bm25),server,DOCUMENTED|LIVE_VERIFIED,claude-fable-5-1|claude-mythos-5-1|claude-fable-5|claude-mythos-5|claude-opus-5|claude-opus-4-8|claude-opus-4-7|claude-opus-4-6|claude-sonnet-4-6|claude-opus-4-5-20251101|claude-sonnet-4-5-20250929|claude-haiku-4-5-20251001,POST /v1/messages|POST /v1/messages/batches,,"Not metered as a server tool (no usage.server_tool_use field); loaded definitions count as input tokens. Live f1: 1,635 input tokens with 6 deferred tools + search tool (vs 581 for one plain tool).",success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-search-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-use-with-prompt-caching|https://platform.claude.com/docs/en/api/messages/create26anthropic,advisor_20260301,Advisor tool (beta),server,DOCUMENTED|BETA|LIVE_VERIFIED,claude-haiku-4-5-20251001|claude-sonnet-4-6|claude-sonnet-5|claude-opus-4-6|claude-opus-4-7|claude-opus-4-8|claude-opus-5|claude-fable-5|claude-mythos-5|claude-fable-5-1|claude-mythos-5-1,POST /v1/messages|POST /v1/messages/batches,advisor-tool-2026-03-01,"Advisor sub-inference billed at the advisor model's rates, reported in usage.iterations[] (type advisor_message); top-level usage = executor only; top-level max_tokens does not bound the advisor.",success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/release-notes/api|https://platform.claude.com/docs/en/build-with-claude/token-counting27anthropic,mcp_toolset,MCP connector toolset (beta),mcp,DOCUMENTED|BETA|LIVE_VERIFIED,claude-fable-5-1|claude-opus-5|claude-sonnet-5|claude-fable-5|claude-opus-4-8|claude-opus-4-7|claude-sonnet-4-6|claude-opus-4-6|claude-opus-4-5-20251101|claude-haiku-4-5-20251001|claude-sonnet-4-5-20250929|claude-mythos-5-1|claude-mythos-5,POST /v1/messages|POST /v1/messages/batches,mcp-client-2025-11-20,"Tokens only (tool definitions fetched from the server count as input; Batches priced the same). Live i1: 2,367 input tokens.",success,https://platform.claude.com/docs/en/agents-and-tools/mcp-connector|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/api/beta/messages/create|https://platform.claude.com/docs/en/api/beta-headers28anthropic,allowed_callers:code_execution_20260120,Programmatic tool calling (allowed_callers / caller),programmatic,DOCUMENTED|LIVE_VERIFIED,claude-fable-5-1|claude-mythos-5-1|claude-fable-5|claude-mythos-5|claude-opus-5|claude-opus-4-8|claude-opus-4-7|claude-opus-4-6|claude-opus-4-5-20251101|claude-sonnet-5|claude-sonnet-4-6|claude-sonnet-4-5-20250929,POST /v1/messages|POST /v1/messages/batches,,"Code execution pricing (free with web_search/web_fetch _20260209+). Programmatic tool results are NOT counted as input/output tokens; only the final code output and Claude's text are. Live g1+g2 on sonnet 4.6: 3,147 + 3,262 input tokens.",success,https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling|https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference|https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools|https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons29gemini,functionDeclarations,Function calling (custom client tools),client,DOCUMENTED|LIVE_VERIFIED,gemini-3.8-flash|gemini-3.7-flash|gemini-3.6-flash|gemini-3.5-flash|gemini-3.5-flash-lite|gemini-3.1-pro-preview|gemini-3.1-pro-preview-customtools|gemini-3.1-flash-lite|gemini-3.1-flash-lite-preview|gemini-3-flash-preview|gemini-3-pro-preview|gemini-2.5-pro|gemini-2.5-flash|gemini-2.5-flash-lite|gemini-robotics-er-2-preview|gemini-robotics-er-1.6-preview|gemini-3.8-live|gemini-3.8-live-extended-thinking|gemini-3.1-flash-live-preview|gemini-2.5-flash-native-audio-preview-12-2025|gemini-robotics-er-2-streaming-preview,"POST /v1beta/models/{model}:generateContent|POST /v1beta/models/{model}:streamGenerateContent|POST /v1beta/models/{model}:countTokens (tools counted)|POST /v1beta/models/{model}:batchGenerateContent (same request schema)|WSS /ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent (setup.tools; toolCall/toolResponse messages; behavior NON_BLOCKING)|POST /v1beta/interactions (as `{""type"":""function"",name,description,parameters}` + `generation_config.tool_choice`)",,No tool fee. Declarations (descriptions + schemas) count as input tokens; functionCall/functionResponse parts and echoed toolCall/toolResponse parts count toward promptTokenCount on the next request. Parallel/compositional calls = extra turns billed as normal tokens.,success,https://ai.google.dev/gemini-api/docs/function-calling|https://ai.google.dev/gemini-api/docs/generate-content/function-calling|https://ai.google.dev/gemini-api/docs/thought-signatures|https://ai.google.dev/gemini-api/docs/generate-content/thought-signatures|https://ai.google.dev/api/generate-content#Tool|https://ai.google.dev/api/generate-content#FunctionDeclaration|https://ai.google.dev/api/generate-content#FunctionCallingConfig|https://ai.google.dev/gemini-api/docs/live-tools|https://ai.google.dev/gemini-api/docs/tool-combination30gemini,googleSearch,Grounding with Google Search,server,DOCUMENTED|ACCOUNT_RESTRICTED,gemini-3.8-flash|gemini-3.7-flash|gemini-3.6-flash|gemini-3.5-flash|gemini-3.5-flash-lite|gemini-3.1-pro-preview|gemini-3.1-pro-preview-customtools|gemini-3.1-flash-lite|gemini-3.1-flash-lite-preview|gemini-3-flash-preview|gemini-3-pro-preview|gemini-3.1-flash-image|gemini-3.1-flash-image-preview|gemini-3-pro-image|gemini-3-pro-image-preview|gemini-2.5-pro|gemini-2.5-flash|gemini-2.5-flash-lite|gemini-robotics-er-2-preview|gemini-robotics-er-1.6-preview|gemini-3.8-live|gemini-3.8-live-extended-thinking|gemini-3.1-flash-live-preview|gemini-2.5-flash-native-audio-preview-12-2025|gemini-robotics-er-2-streaming-preview|gemini-2.0-flash (RETIRED 2026-06-01),"POST /v1beta/models/{model}:generateContent|POST /v1beta/models/{model}:streamGenerateContent|WSS /ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent (setup.tools[{googleSearch:{}}])|POST /v1beta/interactions (as `{""type"":""google_search""}`; search_types: [""web_search"",""image_search""])|POST /v1beta/models/{model}:batchGenerateContent",,"{""free_tier"": ""500 RPD free (shared Flash and Flash-Lite); not available for Pro."", ""gemini_2_5_models"": ""Paid tier: 1,500 RPD free (shared Flash/Flash-Lite), then $35 per 1,000 grounded PROMPTS (billed per prompt)."", ""gemini_3_models"": ""5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search QUERY the model executes (multiple queries in one prompt = multiple billable uses; empty queries ignored). Billing for Gemini 3 started 2026-01-05."", ""image_search"": ""Same $14 per 1,000 requests for text and image-based grounding (Nano Banana 2 pricing table)."", ""tokens"": ""Search-retrieved content is NOT double-charged as tokens (search has its own query-level price); the model's own input/output tokens are billed normally.""}",restricted,https://ai.google.dev/gemini-api/docs/google-search|https://ai.google.dev/gemini-api/docs/generate-content/google-search|https://ai.google.dev/api/generate-content#GoogleSearch|https://ai.google.dev/api/generate-content#GroundingMetadata|https://ai.google.dev/gemini-api/docs/pricing|https://ai.google.dev/gemini-api/docs/generate-content/image-generation|https://ai.google.dev/gemini-api/docs/live-tools|https://ai.google.dev/gemini-api/docs/tool-combination31gemini,googleSearch.searchTypes.imageSearch,Grounding with Google Image Search (searchTypes.imageSearch),server,DOCUMENTED,gemini-3.1-flash-image|gemini-3.1-flash-image-preview,"POST /v1beta/models/{model}:generateContent|POST /v1beta/models/{model}:streamGenerateContent|POST /v1beta/interactions (search_types: [""image_search""])",,"5,000 free search requests/month (shared across Gemini 3.x), then $14 per 1,000 requests for text and image-based grounding.",not_tested,https://ai.google.dev/gemini-api/docs/generate-content/image-generation|https://ai.google.dev/api/generate-content#SearchTypes|https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-image|https://ai.google.dev/gemini-api/docs/pricing32gemini,googleSearchRetrieval,Google Search retrieval (legacy dynamic retrieval),server,DOCUMENTED|LEGACY|DEPRECATED,gemini-2.0-flash (RETIRED 2026-06-01)|gemini-2.0-flash-lite (RETIRED 2026-06-01; search grounding 'Not supported' on its model page)|gemini-1.5-* (RETIRED; not in models list),POST /v1beta/models/{model}:generateContent|POST /v1beta/models/{model}:streamGenerateContent,,"Historically per grounded prompt ($35 / 1,000 grounded prompts, 1,500 RPD free on 2.5-era pricing). No current price line.",not_tested,https://ai.google.dev/api/generate-content#GoogleSearchRetrieval|https://ai.google.dev/api/generate-content#DynamicRetrievalConfig|https://ai.google.dev/gemini-api/docs/google-search|https://ai.google.dev/gemini-api/docs/deprecations|https://ai.google.dev/gemini-api/docs/changelog33gemini,googleMaps,Grounding with Google Maps,server,DOCUMENTED|GA|LIVE_VERIFIED,gemini-3.8-flash|gemini-3.7-flash|gemini-3.6-flash|gemini-3.5-flash|gemini-3.5-flash-lite|gemini-3.1-pro-preview|gemini-3.1-flash-lite|gemini-3.1-flash-lite-preview|gemini-3-flash-preview|gemini-2.5-pro|gemini-2.5-flash|gemini-2.5-flash-lite|gemini-robotics-er-2-preview|gemini-robotics-er-1.6-preview|gemini-2.0-flash (RETIRED 2026-06-01),"POST /v1beta/models/{model}:generateContent|POST /v1beta/models/{model}:streamGenerateContent|POST /v1beta/interactions (as `{""type"":""google_maps""}`)",,"{""maps_guide"": ""$25 / 1K grounded prompts; free tier up to 500 requests per day; a request counts only when the prompt returns ≥1 Google Maps grounded result; multiple Maps queries in one request = one request."", ""note"": ""Documentation is inconsistent ($25/1K prompts vs $14/1K queries for Gemini 3) — DOCUMENTATION_INCOMPLETE; parent agent to verify billing dashboard if needed."", ""pricing_page_gemini_3_model_tables"": ""5,000 prompts per month (free, shared across Gemini 3), then $14 / 1,000 search queries."", ""pricing_page_tools_table"": ""Free tier 500 RPD (not available for Pro). Paid: 1,500 RPD free (shared Flash/Flash-Lite), 10,000 RPD free for Pro, then $25 / 1,000 grounded prompts.""}",success,https://ai.google.dev/gemini-api/docs/maps-grounding|https://ai.google.dev/gemini-api/docs/generate-content/maps-grounding|https://ai.google.dev/api/generate-content#GoogleMaps|https://ai.google.dev/api/generate-content#Maps|https://ai.google.dev/gemini-api/docs/pricing|https://ai.google.dev/gemini-api/docs/changelog34gemini,urlContext,URL context,server,DOCUMENTED|GA|LIVE_VERIFIED,gemini-3.8-flash|gemini-3.7-flash|gemini-3.6-flash|gemini-3.5-flash|gemini-3.5-flash-lite|gemini-3.1-pro-preview|gemini-3.1-pro-preview-customtools|gemini-3.1-flash-lite|gemini-3.1-flash-lite-preview|gemini-3-flash-preview|gemini-3-pro-preview|gemini-2.5-pro|gemini-2.5-flash|gemini-2.5-flash-lite|gemini-robotics-er-2-preview|gemini-robotics-er-1.6-preview,"POST /v1beta/models/{model}:generateContent|POST /v1beta/models/{model}:streamGenerateContent|POST /v1beta/interactions (as `{""type"":""url_context""}`)",,Free tier: free of charge. Paid: retrieved content charged as INPUT tokens at the model's rate (visible as toolUsePromptTokenCount). No per-call fee.,success,https://ai.google.dev/gemini-api/docs/url-context|https://ai.google.dev/gemini-api/docs/generate-content/url-context|https://ai.google.dev/api/generate-content#UrlContext|https://ai.google.dev/api/generate-content#UrlContextMetadata|https://ai.google.dev/gemini-api/docs/pricing|https://ai.google.dev/gemini-api/docs/changelog35gemini,codeExecution,Code execution,server,DOCUMENTED|LIVE_VERIFIED,gemini-3.8-flash|gemini-3.7-flash|gemini-3.6-flash|gemini-3.5-flash|gemini-3.5-flash-lite|gemini-3.1-pro-preview|gemini-3.1-pro-preview-customtools|gemini-3.1-flash-lite|gemini-3.1-flash-lite-preview|gemini-3-flash-preview|gemini-3-pro-preview|gemini-2.5-pro|gemini-2.5-flash|gemini-2.5-flash-lite|gemini-robotics-er-2-preview|gemini-robotics-er-1.6-preview|gemini-2.0-flash (RETIRED 2026-06-01),"POST /v1beta/models/{model}:generateContent|POST /v1beta/models/{model}:streamGenerateContent|POST /v1beta/interactions (as `{""type"":""code_execution""}`)|POST /v1beta/models/{model}:batchGenerateContent",,"No additional charge; standard model token rates. Generated code + execution output + thinking + summary are OUTPUT tokens when created; the prompt, code and results become 'intermediate' INPUT tokens when the model re-reads them (intermediate token count is reported in usageMetadata). No charge for session runtime. Free tier: free of charge.",success,https://ai.google.dev/gemini-api/docs/code-execution|https://ai.google.dev/gemini-api/docs/generate-content/code-execution|https://ai.google.dev/api/generate-content#CodeExecution|https://ai.google.dev/api/generate-content#ExecutableCode|https://ai.google.dev/api/generate-content#CodeExecutionResult|https://ai.google.dev/gemini-api/docs/pricing36gemini,computerUse,Computer Use (Preview),client,DOCUMENTED|PREVIEW|ACCOUNT_RESTRICTED,"gemini-3.8-flash (recommended)|gemini-3.7-flash|gemini-3.6-flash (model page: Supported (Preview))|gemini-3.5-flash|gemini-3.5-flash-lite|gemini-3-flash-preview|gemini-2.5-computer-use-preview-10-2025 (legacy, browser only)|gemini-robotics-er-2-preview|gemini-robotics-er-1.6-preview","POST /v1beta/models/{model}:generateContent|POST /v1beta/models/{model}:streamGenerateContent|POST /v1beta/interactions (as `{""type"":""computer_use""}`)",,No tool fee: charged as regular tokens at the model's price (screenshots are image input tokens). Free tier: not available. Legacy gemini-2.5-computer-use-preview-10-2025 has its own pricing table.,restricted,https://ai.google.dev/gemini-api/docs/computer-use|https://ai.google.dev/gemini-api/docs/generate-content/computer-use|https://ai.google.dev/api/generate-content#ComputerUse|https://ai.google.dev/gemini-api/docs/models/gemini-2.5-computer-use-preview-10-2025|https://ai.google.dev/gemini-api/docs/pricing|https://ai.google.dev/gemini-api/docs/changelog37gemini,fileSearch,File Search (managed RAG),server,DOCUMENTED|PREVIEW|LIVE_VERIFIED,gemini-3.8-flash|gemini-3.7-flash|gemini-3.6-flash|gemini-3.5-flash|gemini-3.5-flash-lite|gemini-3.1-pro-preview (model page: 'Supported (AI Studio only)')|gemini-3.1-flash-lite|gemini-3.1-flash-lite-preview|gemini-3-flash-preview|gemini-3-pro-preview (model page)|gemini-2.5-pro|gemini-2.5-flash-lite|gemini-2.5-flash (model page: Supported; absent from the File Search guide table)|gemini-robotics-er-2-preview|gemini-robotics-er-1.6-preview,"POST /v1beta/models/{model}:generateContent|POST /v1beta/models/{model}:streamGenerateContent|POST /v1beta/interactions (as `{""type"":""file_search"",""file_search_store_names"":[...]}`; also a Deep Research agent tool)|Store management: POST/GET /v1beta/fileSearchStores, GET/DELETE /v1beta/fileSearchStores/{id}, POST /upload/v1beta/fileSearchStores/{id}:uploadToFileSearchStore, POST /v1beta/fileSearchStores/{id}:importFile, GET/DELETE …/documents[/{doc}], GET …/operations/{op}, GET …/upload/operations/{op}, GET /v1beta/fileSearchStores/{id}/media/{blob} (download)",,Indexing: embeddings charged once at indexing time — pricing tools table: $0.15 / 1M tokens (gemini-embedding-2 standard text input is listed at $0.20 / 1M on the same page — DOCUMENTATION_INCOMPLETE). Storage: free. Query-time embeddings: free. Retrieved document tokens: billed as regular input/context tokens of the generating model. Free tier: free of charge.,success,https://ai.google.dev/gemini-api/docs/file-search|https://ai.google.dev/gemini-api/docs/generate-content/file-search|https://ai.google.dev/api/file-search/file-search-stores|https://ai.google.dev/api/file-search/documents|https://ai.google.dev/api/generate-content#FileSearch|https://ai.google.dev/api/generate-content#RetrievedContext|https://ai.google.dev/gemini-api/docs/pricing|https://ai.google.dev/gemini-api/docs/changelog38gemini,mcpServers,"Remote MCP servers (server-side, tools[].mcpServers)",mcp,DOCUMENTED|DOCUMENTATION_INCOMPLETE|UNVERIFIED,UNVERIFIED for generateContent; Interactions API mcp_server: Gemini 3 models (examples use gemini-3.8-flash) and deep-research-* agents,POST /v1beta/models/{model}:generateContent (schema only — UNVERIFIED)|POST /v1beta/interactions (documented: type mcp_server),,Not documented (tokens of tool schemas/results presumably billed as input; UNVERIFIED).,not_tested,https://ai.google.dev/api/generate-content#McpServer|https://ai.google.dev/api/generate-content#StreamableHttpTransport|https://ai.google.dev/gemini-api/docs/function-calling|https://ai.google.dev/gemini-api/docs/deep-research|https://github.com/googleapis/python-genai (README: MCP for Gemini Enterprise Agent Platform)39gemini,mcp (SDK-side),MCP via SDK (client-side automatic tool calling),mcp,DOCUMENTED|BETA,Any model with function calling (examples use gemini-3.8-flash / gemini-2.5-flash).,POST /v1beta/models/{model}:generateContent (SDK wraps it)|POST /v1beta/models/{model}:streamGenerateContent (stream variants)|SDK Chats (AFC is moving to Chats in the next major SDK version per README),,Ordinary token billing per model turn; each AFC round trip is a new generateContent request.,not_tested,https://ai.google.dev/gemini-api/docs/generate-content/function-calling|https://github.com/googleapis/python-genai|https://github.com/googleapis/js-genai40openai,function,Function calling (custom function tool),client,DOCUMENTED|LIVE_VERIFIED,chat-latest|gpt-4.1|gpt-4.1-mini|gpt-4.1-nano|gpt-4o|gpt-4o-mini|gpt-5|gpt-5-chat-latest|gpt-5-codex|gpt-5-mini|gpt-5-nano|gpt-5-pro|gpt-5.1|gpt-5.1-chat-latest|gpt-5.1-codex|gpt-5.1-codex-max|gpt-5.1-codex-mini|gpt-5.2|gpt-5.2-chat-latest|gpt-5.2-codex|gpt-5.2-pro|gpt-5.3-chat-latest|gpt-5.3-codex|gpt-5.4|gpt-5.4-mini|gpt-5.4-nano|gpt-5.4-pro|gpt-5.5|gpt-5.5-pro|gpt-audio-mini|gpt-oss-120b|gpt-oss-20b|o1|o1-pro|o3|o3-mini|o3-pro|o4-mini,POST /v1/responses|POST /v1/chat/completions|POST /v1/realtime (session.tools)|Agents API (agent tool config),,"{""model"": ""Function definitions are injected into the system message and billed as input tokens; call arguments are output tokens."", ""per_call"": null, ""source"": ""https://developers.openai.com/api/docs/pricing#built-in-tools""}",,https://developers.openai.com/api/docs/guides/function-calling|https://developers.openai.com/api/docs/guides/async-tool-calling|https://developers.openai.com/api/reference/resources/responses/methods/create|https://github.com/openai/openai-openapi (openapi-master.yaml)41openai,custom,Custom tool (free-form text or CFG grammar),client,DOCUMENTED|LIVE_VERIFIED,chat-latest|gpt-4.1|gpt-4.1-mini|gpt-4.1-nano|gpt-4o|gpt-4o-mini|gpt-5|gpt-5-chat-latest|gpt-5-codex|gpt-5-mini|gpt-5-nano|gpt-5-pro|gpt-5.1|gpt-5.1-chat-latest|gpt-5.1-codex|gpt-5.1-codex-max|gpt-5.1-codex-mini|gpt-5.2|gpt-5.2-chat-latest|gpt-5.2-codex|gpt-5.2-pro|gpt-5.3-chat-latest|gpt-5.3-codex|gpt-5.4|gpt-5.4-mini|gpt-5.4-nano|gpt-5.4-pro|gpt-5.5|gpt-5.5-pro|gpt-audio-mini|gpt-oss-120b|gpt-oss-20b|o1|o1-pro|o3|o3-mini|o3-pro|o4-mini,POST /v1/responses|POST /v1/chat/completions,,"{""model"": ""Token billing only."", ""source"": ""https://developers.openai.com/api/docs/pricing#built-in-tools""}",,https://developers.openai.com/api/docs/guides/function-calling#custom-tools|https://developers.openai.com/api/reference/resources/responses/methods/create|https://github.com/openai/openai-openapi (openapi-master.yaml)42openai,namespace,Namespace (group of function/custom tools),client,DOCUMENTED|LIVE_VERIFIED,chat-latest|gpt-4.1|gpt-4.1-mini|gpt-4.1-nano|gpt-4o|gpt-4o-mini|gpt-5|gpt-5-chat-latest|gpt-5-codex|gpt-5-mini|gpt-5-nano|gpt-5-pro|gpt-5.1|gpt-5.1-chat-latest|gpt-5.1-codex|gpt-5.1-codex-max|gpt-5.1-codex-mini|gpt-5.2|gpt-5.2-chat-latest|gpt-5.2-codex|gpt-5.2-pro|gpt-5.3-chat-latest|gpt-5.3-codex|gpt-5.4|gpt-5.4-mini|gpt-5.4-nano|gpt-5.4-pro|gpt-5.5|gpt-5.5-pro|gpt-audio-mini|gpt-oss-120b|gpt-oss-20b|o1|o1-pro|o3|o3-mini|o3-pro|o4-mini,POST /v1/responses,,"{""model"": ""Token billing only."", ""source"": ""https://developers.openai.com/api/docs/pricing#built-in-tools""}",,https://developers.openai.com/api/docs/guides/function-calling#namespaces|https://developers.openai.com/api/docs/guides/tools-tool-search|https://developers.openai.com/api/reference/resources/responses/methods/create|https://github.com/openai/openai-openapi (openapi-master.yaml)43openai,tool_search,Tool search (deferred tool loading),hosted,DOCUMENTED|LIVE_VERIFIED,gpt-5.4|gpt-5.4-mini|gpt-5.4-pro|gpt-5.5|gpt-5.6-cyber|gpt-5.6-luna|gpt-5.6-sol|gpt-5.6-terra|gpt-6-astra|gpt-daybreak-blue-latest|gpt-daybreak-red-latest,POST /v1/responses|Agents API (session tools),,"{""model"": ""Token billing only; saves input tokens by not sending deferred definitions up front."", ""source"": ""https://developers.openai.com/api/docs/pricing#built-in-tools""}",,https://developers.openai.com/api/docs/guides/tools-tool-search|https://developers.openai.com/api/reference/resources/responses/methods/create|https://github.com/openai/openai-openapi (openapi-master.yaml)44openai,programmatic_tool_calling,Programmatic Tool Calling,hosted,DOCUMENTED|UNVERIFIED,,POST /v1/responses|Agents API (enabled by default),,"{""model"": ""Token billing only."", ""source"": ""https://developers.openai.com/api/docs/pricing#built-in-tools""}",,https://developers.openai.com/api/docs/guides/tools-programmatic-tool-calling|https://developers.openai.com/api/reference/resources/responses/methods/create|https://github.com/openai/openai-openapi (openapi-master.yaml)45openai,web_search,Web search (hosted),hosted,DOCUMENTED|LIVE_VERIFIED,chat-latest|gpt-4.1|gpt-4.1-mini|gpt-4o|gpt-4o-mini|gpt-4o-mini-audio-preview|gpt-5|gpt-5-chat-latest|gpt-5-codex|gpt-5-mini|gpt-5-nano|gpt-5-pro|gpt-5.1|gpt-5.1-chat-latest|gpt-5.1-codex|gpt-5.1-codex-max|gpt-5.1-codex-mini|gpt-5.2|gpt-5.2-chat-latest|gpt-5.2-codex|gpt-5.2-pro|gpt-5.3-chat-latest|gpt-5.3-codex|gpt-5.4|gpt-5.4-mini|gpt-5.4-nano|gpt-5.4-pro|gpt-5.5|gpt-5.5-pro|gpt-5.6-cyber|gpt-5.6-luna|gpt-5.6-sol|gpt-5.6-terra|gpt-6-astra|gpt-daybreak-blue-latest|gpt-daybreak-red-latest|gpt-oss-120b|gpt-oss-20b|o3|o3-deep-research|o3-pro|o4-mini|o4-mini-deep-research,POST /v1/responses|Realtime/Live (web_search tool in Live sessions)|Agents API,,"{""per_call"": ""$10.00 / 1k calls (web_search, all models; image web search same) + search content tokens billed at model rates"", ""preview"": ""$10/1k (reasoning models) or $25/1k with free content tokens (non-reasoning)"", ""source"": ""https://developers.openai.com/api/docs/pricing#built-in-tools""}",,https://developers.openai.com/api/docs/guides/tools-web-search|https://developers.openai.com/api/docs/pricing#built-in-tools|https://developers.openai.com/api/reference/resources/responses/methods/create|https://github.com/openai/openai-openapi (openapi-master.yaml)46openai,web_search_2025_08_26,Web search (dated snapshot 2025-08-26),hosted,DOCUMENTED|UNVERIFIED,chat-latest|gpt-4.1|gpt-4.1-mini|gpt-4o|gpt-4o-mini|gpt-4o-mini-audio-preview|gpt-5|gpt-5-chat-latest|gpt-5-codex|gpt-5-mini|gpt-5-nano|gpt-5-pro|gpt-5.1|gpt-5.1-chat-latest|gpt-5.1-codex|gpt-5.1-codex-max|gpt-5.1-codex-mini|gpt-5.2|gpt-5.2-chat-latest|gpt-5.2-codex|gpt-5.2-pro|gpt-5.3-chat-latest|gpt-5.3-codex|gpt-5.4|gpt-5.4-mini|gpt-5.4-nano|gpt-5.4-pro|gpt-5.5|gpt-5.5-pro|gpt-5.6-cyber|gpt-5.6-luna|gpt-5.6-sol|gpt-5.6-terra|gpt-6-astra|gpt-daybreak-blue-latest|gpt-daybreak-red-latest|gpt-oss-120b|gpt-oss-20b|o3|o3-deep-research|o3-pro|o4-mini|o4-mini-deep-research,POST /v1/responses,,"{""per_call"": ""$10.00 / 1k calls (web_search, all models; image web search same) + search content tokens billed at model rates"", ""preview"": ""$10/1k (reasoning models) or $25/1k with free content tokens (non-reasoning)"", ""source"": ""https://developers.openai.com/api/docs/pricing#built-in-tools""}",,https://developers.openai.com/api/docs/guides/tools-web-search|https://developers.openai.com/api/reference/resources/responses/methods/create|https://github.com/openai/openai-openapi (openapi-master.yaml)47openai,web_search_preview,Web search preview (legacy),hosted,DOCUMENTED|LEGACY|UNVERIFIED,chat-latest|gpt-4.1|gpt-4.1-mini|gpt-4o|gpt-4o-mini|gpt-4o-mini-audio-preview|gpt-5|gpt-5-chat-latest|gpt-5-codex|gpt-5-mini|gpt-5-nano|gpt-5-pro|gpt-5.1|gpt-5.1-chat-latest|gpt-5.1-codex|gpt-5.1-codex-max|gpt-5.1-codex-mini|gpt-5.2|gpt-5.2-chat-latest|gpt-5.2-codex|gpt-5.2-pro|gpt-5.3-chat-latest|gpt-5.3-codex|gpt-5.4|gpt-5.4-mini|gpt-5.4-nano|gpt-5.4-pro|gpt-5.5|gpt-5.5-pro|gpt-5.6-cyber|gpt-5.6-luna|gpt-5.6-sol|gpt-5.6-terra|gpt-6-astra|gpt-daybreak-blue-latest|gpt-daybreak-red-latest|gpt-oss-120b|gpt-oss-20b|o3|o3-deep-research|o3-pro|o4-mini|o4-mini-deep-research,POST /v1/responses,,"{""per_call"": ""$10.00 / 1k calls (web_search, all models; image web search same) + search content tokens billed at model rates"", ""preview"": ""$10/1k (reasoning models) or $25/1k with free content tokens (non-reasoning)"", ""source"": ""https://developers.openai.com/api/docs/pricing#built-in-tools""}",,https://developers.openai.com/api/docs/guides/tools-web-search|https://developers.openai.com/api/reference/resources/responses/methods/create|https://github.com/openai/openai-openapi (openapi-master.yaml)48openai,web_search_preview_2025_03_11,Web search preview (dated snapshot 2025-03-11),hosted,DOCUMENTED|LEGACY|UNVERIFIED,chat-latest|gpt-4.1|gpt-4.1-mini|gpt-4o|gpt-4o-mini|gpt-4o-mini-audio-preview|gpt-5|gpt-5-chat-latest|gpt-5-codex|gpt-5-mini|gpt-5-nano|gpt-5-pro|gpt-5.1|gpt-5.1-chat-latest|gpt-5.1-codex|gpt-5.1-codex-max|gpt-5.1-codex-mini|gpt-5.2|gpt-5.2-chat-latest|gpt-5.2-codex|gpt-5.2-pro|gpt-5.3-chat-latest|gpt-5.3-codex|gpt-5.4|gpt-5.4-mini|gpt-5.4-nano|gpt-5.4-pro|gpt-5.5|gpt-5.5-pro|gpt-5.6-cyber|gpt-5.6-luna|gpt-5.6-sol|gpt-5.6-terra|gpt-6-astra|gpt-daybreak-blue-latest|gpt-daybreak-red-latest|gpt-oss-120b|gpt-oss-20b|o3|o3-deep-research|o3-pro|o4-mini|o4-mini-deep-research,POST /v1/responses,,"{""per_call"": ""$10.00 / 1k calls (web_search, all models; image web search same) + search content tokens billed at model rates"", ""preview"": ""$10/1k (reasoning models) or $25/1k with free content tokens (non-reasoning)"", ""source"": ""https://developers.openai.com/api/docs/pricing#built-in-tools""}",,https://developers.openai.com/api/docs/guides/tools-web-search|https://developers.openai.com/api/reference/resources/responses/methods/create|https://github.com/openai/openai-openapi (openapi-master.yaml)49openai,file_search,File search (vector stores),hosted,DOCUMENTED|LIVE_VERIFIED,chat-latest|gpt-4.1|gpt-4.1-mini|gpt-4.1-nano|gpt-4o|gpt-4o-mini|gpt-4o-mini-audio-preview|gpt-5|gpt-5-chat-latest|gpt-5-mini|gpt-5-nano|gpt-5-pro|gpt-5.1|gpt-5.1-chat-latest|gpt-5.2|gpt-5.2-chat-latest|gpt-5.2-pro|gpt-5.3-chat-latest|gpt-5.4|gpt-5.4-mini|gpt-5.4-nano|gpt-5.4-pro|gpt-5.5|gpt-5.5-pro|gpt-5.6-cyber|gpt-5.6-luna|gpt-5.6-sol|gpt-5.6-terra|gpt-6-astra|gpt-daybreak-blue-latest|gpt-daybreak-red-latest|o1|o1-mini|o1-pro|o3|o3-mini|o3-pro|o4-mini,POST /v1/responses|Assistants API (legacy),,"{""per_call"": ""$2.50 / 1k calls"", ""source"": ""https://developers.openai.com/api/docs/pricing#built-in-tools"", ""storage"": ""$0.10 / GB / day (1 GB free)""}",,https://developers.openai.com/api/docs/guides/tools-file-search|https://developers.openai.com/api/docs/pricing#built-in-tools|https://developers.openai.com/api/reference/resources/responses/methods/create|https://github.com/openai/openai-openapi (openapi-master.yaml)50openai,code_interpreter,Code interpreter (Python sandbox container),hosted,DOCUMENTED|LIVE_VERIFIED,chat-latest|gpt-4.1|gpt-4.1-mini|gpt-4.1-nano|gpt-4o|gpt-4o-mini|gpt-4o-mini-audio-preview|gpt-5|gpt-5-chat-latest|gpt-5-mini|gpt-5-nano|gpt-5.1|gpt-5.1-chat-latest|gpt-5.2|gpt-5.2-chat-latest|gpt-5.3-chat-latest|gpt-5.4|gpt-5.4-mini|gpt-5.4-nano|gpt-5.5|gpt-5.5-pro|gpt-5.6-cyber|gpt-5.6-luna|gpt-5.6-sol|gpt-5.6-terra|gpt-6-astra|gpt-daybreak-blue-latest|gpt-daybreak-red-latest|gpt-oss-120b|gpt-oss-20b|o1-mini|o3|o3-deep-research|o3-mini|o4-mini|o4-mini-deep-research,POST /v1/responses|Assistants API (legacy),,"{""per_session"": ""1 GB $0.03 · 4 GB $0.12 · 16 GB $0.48 · 64 GB $1.92 per 20-minute session per container (shared with hosted shell)"", ""source"": ""https://developers.openai.com/api/docs/pricing#built-in-tools""}",,https://developers.openai.com/api/docs/guides/tools-code-interpreter|https://developers.openai.com/api/reference/resources/containers|https://developers.openai.com/api/docs/pricing#built-in-tools|https://developers.openai.com/api/reference/resources/responses/methods/create|https://github.com/openai/openai-openapi (openapi-master.yaml)51openai,computer_use_preview,Computer use (preview tool + computer-use-preview model),client,DOCUMENTED|PREVIEW|ACCOUNT_RESTRICTED,gpt-5.4|gpt-5.4-mini|gpt-5.4-pro|gpt-5.5|gpt-5.6-cyber|gpt-5.6-luna|gpt-5.6-sol|gpt-5.6-terra|gpt-6-astra|gpt-daybreak-blue-latest|gpt-daybreak-red-latest,POST /v1/responses,,"{""model"": ""computer-use-preview $3 / 1M input, $12 / 1M output (model page); newer models at their own rates"", ""source"": ""https://developers.openai.com/api/docs/models/computer-use-preview""}",,https://developers.openai.com/api/docs/guides/tools-computer-use|https://developers.openai.com/api/docs/guides/tools-computer-use-integration|https://developers.openai.com/api/docs/models/computer-use-preview|https://developers.openai.com/api/reference/resources/responses/methods/create|https://github.com/openai/openai-openapi (openapi-master.yaml)52openai,computer,Computer tool (current),client,DOCUMENTED|UNVERIFIED,gpt-5.4|gpt-5.4-mini|gpt-5.4-pro|gpt-5.5|gpt-5.6-cyber|gpt-5.6-luna|gpt-5.6-sol|gpt-5.6-terra|gpt-6-astra|gpt-daybreak-blue-latest|gpt-daybreak-red-latest,POST /v1/responses,,"{""model"": ""Token billing (images as input tokens)"", ""source"": ""https://developers.openai.com/api/docs/pricing#built-in-tools""}",,https://developers.openai.com/api/docs/guides/tools-computer-use|https://developers.openai.com/api/docs/guides/tools-computer-use-integration|https://developers.openai.com/api/reference/resources/responses/methods/create|https://github.com/openai/openai-openapi (openapi-master.yaml)53openai,image_generation,Image generation tool,hosted,DOCUMENTED|LIVE_VERIFIED,chat-latest|gpt-4.1|gpt-4.1-nano|gpt-4o|gpt-4o-mini|gpt-5|gpt-5-chat-latest|gpt-5-nano|gpt-5-pro|gpt-5.1|gpt-5.1-chat-latest|gpt-5.2|gpt-5.2-chat-latest|gpt-5.2-pro|gpt-5.3-chat-latest|gpt-5.4|gpt-5.4-mini|gpt-5.4-nano|gpt-5.4-pro|gpt-5.5|gpt-5.5-pro|gpt-5.6-cyber|gpt-5.6-luna|gpt-5.6-sol|gpt-5.6-terra|gpt-6-astra|gpt-daybreak-blue-latest|gpt-daybreak-red-latest|o3|o3-mini|o3-pro,POST /v1/responses,,"{""per_image"": ""Image model token pricing (see pricing fragment / image generation guide calculator); mainline model tokens billed separately"", ""source"": ""https://developers.openai.com/api/docs/pricing#image-generation""}",,https://developers.openai.com/api/docs/guides/tools-image-generation|https://developers.openai.com/api/reference/resources/responses/methods/create|https://github.com/openai/openai-openapi (openapi-master.yaml)54openai,mcp,"Remote MCP servers, connectors and Secure MCP Tunnel",mcp,DOCUMENTED|LIVE_VERIFIED,chat-latest|gpt-4.1|gpt-4.1-mini|gpt-4.1-nano|gpt-4o|gpt-4o-mini|gpt-4o-mini-audio-preview|gpt-5|gpt-5-chat-latest|gpt-5-mini|gpt-5-nano|gpt-5-pro|gpt-5.1|gpt-5.1-chat-latest|gpt-5.2|gpt-5.2-chat-latest|gpt-5.2-pro|gpt-5.3-chat-latest|gpt-5.4|gpt-5.4-mini|gpt-5.4-nano|gpt-5.4-pro|gpt-5.5|gpt-5.5-pro|gpt-5.6-cyber|gpt-5.6-luna|gpt-5.6-sol|gpt-5.6-terra|gpt-6-astra|gpt-daybreak-blue-latest|gpt-daybreak-red-latest|gpt-oss-120b|gpt-oss-20b|o1|o1-mini|o1-pro|o3|o3-deep-research|o3-mini|o3-pro|o4-mini|o4-mini-deep-research,POST /v1/responses|POST /v1/realtime (mcp tool)|Agents API (MCP connections)|Deep research models,,"{""per_call"": ""No OpenAI per-call fee; imported tool definitions and tool outputs are billed as model tokens"", ""source"": ""https://developers.openai.com/api/docs/pricing#built-in-tools""}",,https://developers.openai.com/api/docs/guides/tools-connectors-mcp|https://developers.openai.com/api/docs/guides/secure-mcp-tunnels|https://developers.openai.com/api/docs/guides/realtime-mcp|https://developers.openai.com/api/reference/resources/responses/methods/create|https://github.com/openai/openai-openapi (openapi-master.yaml)55openai,shell,Shell tool (hosted container or local runtime),hosted,DOCUMENTED|LIVE_VERIFIED,gpt-5.2|gpt-5.2-codex|gpt-5.3-codex|gpt-5.4|gpt-5.4-mini|gpt-5.4-nano|gpt-5.5|gpt-5.5-pro|gpt-5.6-cyber|gpt-5.6-luna|gpt-5.6-sol|gpt-5.6-terra|gpt-6-astra|gpt-daybreak-blue-latest|gpt-daybreak-red-latest,POST /v1/responses,,"{""local"": ""Token billing only"", ""per_session"": ""Hosted containers: same rates as code interpreter (1 GB $0.03 … 64 GB $1.92 per 20-min session)"", ""source"": ""https://developers.openai.com/api/docs/pricing#built-in-tools""}",,https://developers.openai.com/api/docs/guides/tools-shell|https://developers.openai.com/api/docs/pricing#built-in-tools|https://developers.openai.com/api/reference/resources/responses/methods/create|https://github.com/openai/openai-openapi (openapi-master.yaml)56openai,local_shell,"Local shell (legacy, codex-mini-latest)",client,DOCUMENTED|LEGACY|FAILED_VERIFICATION,codex-mini-latest,POST /v1/responses,,"{""model"": ""Token billing only"", ""source"": ""https://developers.openai.com/api/docs/pricing#built-in-tools""}",,https://developers.openai.com/api/docs/guides/tools-local-shell|https://developers.openai.com/api/reference/resources/responses/methods/create|https://github.com/openai/openai-openapi (openapi-master.yaml)57openai,apply_patch,Apply patch (structured file diffs),client,DOCUMENTED|LIVE_VERIFIED,gpt-5.1|gpt-5.2|gpt-5.4|gpt-5.4-mini|gpt-5.4-nano|gpt-5.4-pro|gpt-5.5|gpt-5.6-cyber|gpt-5.6-luna|gpt-5.6-sol|gpt-5.6-terra|gpt-6-astra|gpt-daybreak-blue-latest|gpt-daybreak-red-latest,POST /v1/responses,,"{""model"": ""Token billing only"", ""source"": ""https://developers.openai.com/api/docs/pricing#built-in-tools""}",,https://developers.openai.com/api/docs/guides/tools-apply-patch|https://developers.openai.com/api/reference/resources/responses/methods/create|https://github.com/openai/openai-openapi (openapi-master.yaml)58openai,skill_reference,Skills (attachments for hosted shell / containers) — not a tool type,hosted,DOCUMENTED|LIVE_VERIFIED,gpt-5.2|gpt-5.2-codex|gpt-5.3-codex|gpt-5.4|gpt-5.4-mini|gpt-5.4-nano|gpt-5.5|gpt-5.6-cyber|gpt-5.6-luna|gpt-5.6-sol|gpt-5.6-terra|gpt-6-astra|gpt-daybreak-blue-latest|gpt-daybreak-red-latest,POST /v1/responses (tools[type=shell].environment.skills)|POST /v1/containers (skills)|Agents API sandboxes,,"{""model"": ""Container session + tokens"", ""source"": ""https://developers.openai.com/api/docs/pricing#built-in-tools""}",,https://developers.openai.com/api/docs/guides/tools-skills|https://developers.openai.com/api/reference/resources/skills|https://developers.openai.com/api/reference/resources/responses/methods/create|https://github.com/openai/openai-openapi (openapi-master.yaml)59xai,function,Function calling,client,DOCUMENTED|LIVE_VERIFIED,grok-4.6|grok-4.5|grok-4.3|grok-4.20-0309-reasoning|grok-4.20-0309-non-reasoning|grok-4.20-multi-agent-0309|grok-build-0.1,POST /v1/chat/completions|POST /v1/responses|POST /v1/messages (Anthropic shape: name/description/input_schema)|Batch API,,Tokens only (no per-call fee).,success,https://docs.x.ai/developers/tools/function-calling|https://docs.x.ai/openapi.json60xai,web_search,Web Search,server,DOCUMENTED|LIVE_VERIFIED,grok-4.6|grok-4.5|grok-4.3|grok-4.20-0309-reasoning|grok-4.20-0309-non-reasoning|grok-4.20-multi-agent-0309|grok-build-0.1,POST /v1/responses|Batch API (responses body),,$5 per 1k successful calls (+ tokens); image search billed as web search; view_image billed as image tokens.,success,https://docs.x.ai/developers/tools/web-search|https://docs.x.ai/developers/tools/citations|https://docs.x.ai/developers/pricing|https://docs.x.ai/openapi.json61xai,x_search,X Search,server,DOCUMENTED|LIVE_VERIFIED|LIVE_DISCOVERED,grok-4.6|grok-4.5|grok-4.3|grok-4.20-0309-reasoning|grok-4.20-0309-non-reasoning|grok-4.20-multi-agent-0309|grok-build-0.1,POST /v1/responses|Batch API,,$5 per 1k calls until 2026-09-21 12:00 PT; then $5 per 1k posts fetched + $10 per 1k user profiles fetched.,success,https://docs.x.ai/developers/tools/x-search|https://docs.x.ai/developers/pricing|https://docs.x.ai/openapi.json62xai,code_interpreter,Code Execution (Code Interpreter),server,DOCUMENTED|LIVE_VERIFIED,grok-4.6|grok-4.5|grok-4.3|grok-4.20-0309-reasoning|grok-4.20-0309-non-reasoning|grok-4.20-multi-agent-0309|grok-build-0.1,POST /v1/responses|Batch API,,$5 per 1k calls + tokens.,success,https://docs.x.ai/developers/tools/code-execution|https://docs.x.ai/developers/tools/streaming-and-sync|https://docs.x.ai/openapi.json63xai,file_search,Collections Search (File Search),server,DOCUMENTED|LIVE_VERIFIED,grok-4.6|grok-4.5|grok-4.3|grok-4.20-0309-reasoning|grok-4.20-0309-non-reasoning|grok-4.20-multi-agent-0309|grok-build-0.1,POST /v1/responses|Batch API,,$2.50 per 1k calls + tokens; storage $0.10/GiB/day.,success,https://docs.x.ai/developers/tools/collections-search|https://docs.x.ai/developers/files/collections|https://docs.x.ai/openapi.json64xai,mcp,Remote MCP,mcp,DOCUMENTED|LIVE_VERIFIED,grok-4.6|grok-4.5|grok-4.3|grok-4.20-0309-reasoning|grok-4.20-0309-non-reasoning|grok-4.20-multi-agent-0309|grok-build-0.1,POST /v1/responses|Batch API|Speech-to-Speech API,,No per-call fee; tokens only (tool outputs count as input tokens).,success,https://docs.x.ai/developers/tools/remote-mcp|https://docs.x.ai/openapi.json65xai,image_generation,Image Generation (tool),server,DOCUMENTED|LIVE_VERIFIED,grok-4.6|grok-4.5|grok-4.3|grok-4.20-0309-reasoning|grok-4.20-0309-non-reasoning|grok-4.20-multi-agent-0309|grok-build-0.1,POST /v1/responses,,Imagine API per-image rates.,success,https://docs.x.ai/developers/tools/image-generation|https://docs.x.ai/openapi.json66xai,attachment_search,Attachment search (implicit),server-implicit,DOCUMENTED|LIVE_VERIFIED,grok-4.6|grok-4.5|grok-4.3|grok-4.20-0309-reasoning|grok-4.20-0309-non-reasoning|grok-4.20-multi-agent-0309|grok-build-0.1,POST /v1/responses,,$10 per 1k calls (File Attachments).,success,https://docs.x.ai/developers/model-capabilities/files/chat-with-files|https://docs.x.ai/developers/pricing67xai,view_image,Image understanding (view_image / view_x_video sub-tools),server-subtool,DOCUMENTED,grok-4.6|grok-4.5|grok-4.3|grok-4.20-0309-reasoning|grok-4.20-0309-non-reasoning|grok-4.20-multi-agent-0309|grok-build-0.1,POST /v1/responses (via web_search / x_search options),,No invocation fee; image tokens billed.,success,https://docs.x.ai/developers/tools/web-search|https://docs.x.ai/developers/tools/x-search|https://docs.x.ai/developers/tools/tool-usage-details|https://docs.x.ai/developers/pricing68xai,shell,Shell (local),client,DOCUMENTED|LIVE_VERIFIED,grok-4.6|grok-4.5|grok-4.3|grok-4.20-0309-reasoning|grok-4.20-0309-non-reasoning|grok-4.20-multi-agent-0309|grok-build-0.1,POST /v1/responses,,Tokens only.,success,https://docs.x.ai/openapi.json69xai,tool_search,Tool search (deferred tool loading),hosted,DOCUMENTED|ACCOUNT_RESTRICTED,grok-4.6|grok-4.5|grok-4.3|grok-4.20-0309-reasoning|grok-4.20-0309-non-reasoning|grok-4.20-multi-agent-0309|grok-build-0.1,POST /v1/responses,,,restricted,https://docs.x.ai/openapi.json70xai,live_search,Live Search (legacy chat tool),server,DOCUMENTED|RETIRED,,POST /v1/chat/completions (410),,,failure,https://docs.x.ai/developers/rest-api-reference/inference/chat-completions|https://docs.x.ai/openapi.json71