{ "generated_at": "2026-07-04T10:48:54Z", "count": 135, "version": "0.5", "models": [ { "provider": "openai", "model_id": "gpt-5.5", "display_name": "GPT-5.5", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 5.0, "output_per_mtok": 30.0, "cached_input_per_mtok": 0.5, "batch_discount_pct": null }, "context_window_tokens": 1050000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "knowledge_cutoff": "Dec 01, 2025", "sources": [ { "url": "https://developers.openai.com/api/docs/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok" ], "quote": "gpt-5.5$5.00$0.50$30.00$10.00$1.00$45.00" }, { "url": "https://developers.openai.com/api/docs/models/compare", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "context_window_tokens", "max_output_tokens", "knowledge_cutoff", "modalities" ], "quote": "GPT-5.5 ... Input $5.00 Cached Input $0.50 Output $30.00 Context Window 1,050,000 Max Output Tokens 128,000 Knowledge Cutoff Dec 01, 2025 Supported Features Streaming Function calling Structured outputs Image input" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": "OpenAI pricing records the standard short-context tier; long-context pricing, where present, is noted in the cited quote.", "permalink": "/models/openai/gpt-5_5.html" }, { "provider": "openai", "model_id": "gpt-5.5-pro", "display_name": "GPT-5.5 Pro", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 30.0, "output_per_mtok": 180.0, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": 1050000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "knowledge_cutoff": "Dec 01, 2025", "sources": [ { "url": "https://developers.openai.com/api/docs/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok" ], "quote": "gpt-5.5-pro$30.00-$180.00$60.00-$270.00" }, { "url": "https://developers.openai.com/api/docs/models/compare", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "context_window_tokens", "max_output_tokens", "knowledge_cutoff", "modalities" ], "quote": "GPT-5.5 Pro ... Input $30.00 Cached Input - Output $180.00 Context Window 1,050,000 Max Output Tokens 128,000 Knowledge Cutoff Dec 01, 2025 Supported Features Streaming Function calling Structured outputs Image input" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": "OpenAI pricing records the standard short-context tier; long-context pricing, where present, is noted in the cited quote.", "permalink": "/models/openai/gpt-5_5-pro.html" }, { "provider": "openai", "model_id": "gpt-5.4", "display_name": "GPT-5.4", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 2.5, "output_per_mtok": 15.0, "cached_input_per_mtok": 0.25, "batch_discount_pct": null }, "context_window_tokens": 1050000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "knowledge_cutoff": "Aug 31, 2025", "sources": [ { "url": "https://developers.openai.com/api/docs/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok" ], "quote": "gpt-5.4$2.50$0.25$15.00$5.00$0.50$22.50" }, { "url": "https://developers.openai.com/api/docs/models/compare", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "context_window_tokens", "max_output_tokens", "knowledge_cutoff", "modalities" ], "quote": "GPT-5.4 ... Input $2.50 Cached Input $0.25 Output $15.00 Context Window 1,050,000 Max Output Tokens 128,000 Knowledge Cutoff Aug 31, 2025 Supported Features Streaming Function calling Structured outputs Image input" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": "OpenAI pricing records the standard short-context tier; long-context pricing, where present, is noted in the cited quote.", "permalink": "/models/openai/gpt-5_4.html" }, { "provider": "anthropic", "model_id": "claude-fable-5", "display_name": "Claude Fable 5", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 10, "output_per_mtok": 50, "cached_input_per_mtok": 1, "batch_discount_pct": null }, "context_window_tokens": 1000000, "context_window_notation": "1M", "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "knowledge_cutoff": "Jan 2026", "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok" ], "quote": "Claude Fable 5$10 / MTok$12.50 / MTok$20 / MTok$1 / MTok$50 / MTok Claude Opus 4.8$5 / MTok$6.25 / MTok$10 / MTok$0.50 / MTok$25 / MTok Claude Opus 4.7$5 / MTok$6.25 / MTok$10 / MTok$0.50 / MTok$25 / MTok Claude Opus 4.6$5 / MTok$6.25 / MTok$10 / MTok$0.50 / MTok$25 / MTok Claude Sonnet 5 through August 31, 2026 $2 / MTok$2.50 / MTok$4 / MTok$0.20 / MTok$10 / MTok Claude Haiku 4.5$1 / MTok$1.25 / MTok$2 / MTok$0.10 / MTok$5 / MTok" }, { "url": "https://platform.claude.com/docs/en/about-claude/models/overview", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "modalities" ], "quote": "All current Claude models support text and image input, text output, multilingual capabilities, and vision." }, { "url": "https://platform.claude.com/docs/en/about-claude/models/overview", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "model_id", "context_window_tokens", "max_output_tokens", "knowledge_cutoff" ], "quote": "Claude API ID claude-fable-5 claude-opus-4-8 claude-sonnet-5 claude-haiku-4-5-20251001 ... Context window 1M tokens 1M tokens 1M tokens 200k tokens Max output 128k tokens 128k tokens 128k tokens 64k tokens Reliable knowledge cutoff Jan 2026 Jan 2026 Jan 2026 Feb 2025" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": null, "permalink": "/models/anthropic/claude-fable-5.html" }, { "provider": "anthropic", "model_id": "claude-opus-4-8", "display_name": "Claude Opus 4.8", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 5, "output_per_mtok": 25, "cached_input_per_mtok": 0.5, "batch_discount_pct": null }, "context_window_tokens": 1000000, "context_window_notation": "1M", "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "knowledge_cutoff": "Jan 2026", "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok" ], "quote": "Claude Fable 5$10 / MTok$12.50 / MTok$20 / MTok$1 / MTok$50 / MTok Claude Opus 4.8$5 / MTok$6.25 / MTok$10 / MTok$0.50 / MTok$25 / MTok Claude Opus 4.7$5 / MTok$6.25 / MTok$10 / MTok$0.50 / MTok$25 / MTok Claude Opus 4.6$5 / MTok$6.25 / MTok$10 / MTok$0.50 / MTok$25 / MTok Claude Sonnet 5 through August 31, 2026 $2 / MTok$2.50 / MTok$4 / MTok$0.20 / MTok$10 / MTok Claude Haiku 4.5$1 / MTok$1.25 / MTok$2 / MTok$0.10 / MTok$5 / MTok" }, { "url": "https://platform.claude.com/docs/en/about-claude/models/overview", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "modalities" ], "quote": "All current Claude models support text and image input, text output, multilingual capabilities, and vision." }, { "url": "https://platform.claude.com/docs/en/about-claude/models/overview", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "model_id", "context_window_tokens", "max_output_tokens", "knowledge_cutoff" ], "quote": "Claude API ID claude-fable-5 claude-opus-4-8 claude-sonnet-5 claude-haiku-4-5-20251001 ... Context window 1M tokens 1M tokens 1M tokens 200k tokens Max output 128k tokens 128k tokens 128k tokens 64k tokens Reliable knowledge cutoff Jan 2026 Jan 2026 Jan 2026 Feb 2025" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": null, "permalink": "/models/anthropic/claude-opus-4-8.html" }, { "provider": "anthropic", "model_id": "claude-opus-4-7", "display_name": "Claude Opus 4.7", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 5, "output_per_mtok": 25, "cached_input_per_mtok": 0.5, "batch_discount_pct": null }, "context_window_tokens": 1000000, "context_window_notation": "1M", "max_output_tokens": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok" ], "quote": "Claude Fable 5$10 / MTok$12.50 / MTok$20 / MTok$1 / MTok$50 / MTok Claude Opus 4.8$5 / MTok$6.25 / MTok$10 / MTok$0.50 / MTok$25 / MTok Claude Opus 4.7$5 / MTok$6.25 / MTok$10 / MTok$0.50 / MTok$25 / MTok Claude Opus 4.6$5 / MTok$6.25 / MTok$10 / MTok$0.50 / MTok$25 / MTok Claude Sonnet 5 through August 31, 2026 $2 / MTok$2.50 / MTok$4 / MTok$0.20 / MTok$10 / MTok Claude Haiku 4.5$1 / MTok$1.25 / MTok$2 / MTok$0.10 / MTok$5 / MTok" }, { "url": "https://platform.claude.com/docs/en/about-claude/models/overview", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "modalities" ], "quote": "All current Claude models support text and image input, text output, multilingual capabilities, and vision." }, { "url": "https://platform.claude.com/docs/en/about-claude/models/model-ids-and-versions", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "model_id" ], "quote": "For example: `claude-sonnet-4-6`, `claude-sonnet-5`, `claude-opus-4-6`, `claude-opus-4-7`, and `claude-opus-4-8`" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "context_window_tokens" ], "quote": "Claude Fable 5, Claude Mythos 5, Claude Mythos Preview, Claude Opus 4.8, Opus 4.7, Opus 4.6, Sonnet 5, and Sonnet 4.6 include the full 1M token context window at standard pricing." } ], "verified_at": "2026-07-04T05:55:32Z", "notes": null, "permalink": "/models/anthropic/claude-opus-4-7.html" }, { "provider": "anthropic", "model_id": "claude-opus-4-6", "display_name": "Claude Opus 4.6", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 5, "output_per_mtok": 25, "cached_input_per_mtok": 0.5, "batch_discount_pct": null }, "context_window_tokens": 1000000, "context_window_notation": "1M", "max_output_tokens": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok" ], "quote": "Claude Fable 5$10 / MTok$12.50 / MTok$20 / MTok$1 / MTok$50 / MTok Claude Opus 4.8$5 / MTok$6.25 / MTok$10 / MTok$0.50 / MTok$25 / MTok Claude Opus 4.7$5 / MTok$6.25 / MTok$10 / MTok$0.50 / MTok$25 / MTok Claude Opus 4.6$5 / MTok$6.25 / MTok$10 / MTok$0.50 / MTok$25 / MTok Claude Sonnet 5 through August 31, 2026 $2 / MTok$2.50 / MTok$4 / MTok$0.20 / MTok$10 / MTok Claude Haiku 4.5$1 / MTok$1.25 / MTok$2 / MTok$0.10 / MTok$5 / MTok" }, { "url": "https://platform.claude.com/docs/en/about-claude/models/overview", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "modalities" ], "quote": "All current Claude models support text and image input, text output, multilingual capabilities, and vision." }, { "url": "https://platform.claude.com/docs/en/about-claude/models/model-ids-and-versions", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "model_id" ], "quote": "For example: `claude-sonnet-4-6`, `claude-sonnet-5`, `claude-opus-4-6`, `claude-opus-4-7`, and `claude-opus-4-8`" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "context_window_tokens" ], "quote": "Claude Fable 5, Claude Mythos 5, Claude Mythos Preview, Claude Opus 4.8, Opus 4.7, Opus 4.6, Sonnet 5, and Sonnet 4.6 include the full 1M token context window at standard pricing." } ], "verified_at": "2026-07-04T05:55:32Z", "notes": null, "permalink": "/models/anthropic/claude-opus-4-6.html" }, { "provider": "anthropic", "model_id": "claude-sonnet-5", "display_name": "Claude Sonnet 5", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 2, "output_per_mtok": 10, "cached_input_per_mtok": 0.2, "batch_discount_pct": null }, "context_window_tokens": 1000000, "context_window_notation": "1M", "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "knowledge_cutoff": "Jan 2026", "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok" ], "quote": "Claude Fable 5$10 / MTok$12.50 / MTok$20 / MTok$1 / MTok$50 / MTok Claude Opus 4.8$5 / MTok$6.25 / MTok$10 / MTok$0.50 / MTok$25 / MTok Claude Opus 4.7$5 / MTok$6.25 / MTok$10 / MTok$0.50 / MTok$25 / MTok Claude Opus 4.6$5 / MTok$6.25 / MTok$10 / MTok$0.50 / MTok$25 / MTok Claude Sonnet 5 through August 31, 2026 $2 / MTok$2.50 / MTok$4 / MTok$0.20 / MTok$10 / MTok Claude Haiku 4.5$1 / MTok$1.25 / MTok$2 / MTok$0.10 / MTok$5 / MTok" }, { "url": "https://platform.claude.com/docs/en/about-claude/models/overview", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "modalities" ], "quote": "All current Claude models support text and image input, text output, multilingual capabilities, and vision." }, { "url": "https://platform.claude.com/docs/en/about-claude/models/overview", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "model_id", "context_window_tokens", "max_output_tokens", "knowledge_cutoff" ], "quote": "Claude API ID claude-fable-5 claude-opus-4-8 claude-sonnet-5 claude-haiku-4-5-20251001 ... Context window 1M tokens 1M tokens 1M tokens 200k tokens Max output 128k tokens 128k tokens 128k tokens 64k tokens Reliable knowledge cutoff Jan 2026 Jan 2026 Jan 2026 Feb 2025" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": null, "permalink": "/models/anthropic/claude-sonnet-5.html" }, { "provider": "anthropic", "model_id": "claude-haiku-4-5-20251001", "display_name": "Claude Haiku 4.5", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 1, "output_per_mtok": 5, "cached_input_per_mtok": 0.1, "batch_discount_pct": null }, "context_window_tokens": 200000, "context_window_notation": "200k", "max_output_tokens": 64000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "knowledge_cutoff": "Feb 2025", "sources": [ { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok" ], "quote": "Claude Fable 5$10 / MTok$12.50 / MTok$20 / MTok$1 / MTok$50 / MTok Claude Opus 4.8$5 / MTok$6.25 / MTok$10 / MTok$0.50 / MTok$25 / MTok Claude Opus 4.7$5 / MTok$6.25 / MTok$10 / MTok$0.50 / MTok$25 / MTok Claude Opus 4.6$5 / MTok$6.25 / MTok$10 / MTok$0.50 / MTok$25 / MTok Claude Sonnet 5 through August 31, 2026 $2 / MTok$2.50 / MTok$4 / MTok$0.20 / MTok$10 / MTok Claude Haiku 4.5$1 / MTok$1.25 / MTok$2 / MTok$0.10 / MTok$5 / MTok" }, { "url": "https://platform.claude.com/docs/en/about-claude/models/overview", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "modalities" ], "quote": "All current Claude models support text and image input, text output, multilingual capabilities, and vision." }, { "url": "https://platform.claude.com/docs/en/about-claude/models/overview", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "model_id", "context_window_tokens", "max_output_tokens", "knowledge_cutoff" ], "quote": "Claude API ID claude-fable-5 claude-opus-4-8 claude-sonnet-5 claude-haiku-4-5-20251001 ... Context window 1M tokens 1M tokens 1M tokens 200k tokens Max output 128k tokens 128k tokens 128k tokens 64k tokens Reliable knowledge cutoff Jan 2026 Jan 2026 Jan 2026 Feb 2025" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": null, "permalink": "/models/anthropic/claude-haiku-4-5-20251001.html" }, { "provider": "google", "model_id": "gemini-3.1-flash-lite", "display_name": "Gemini 3.1 Flash-Lite", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.25, "output_per_mtok": 1.5, "cached_input_per_mtok": 0.025, "batch_discount_pct": null }, "context_window_tokens": null, "max_output_tokens": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok", "modalities" ], "quote": "Gemini 3.1 Flash-Lite `gemini-3.1-flash-lite` ... Input price Free of charge $0.25 (text / image / video) $0.50 (audio) Output price (including thinking tokens) Free of charge $1.50 Context caching price Not available $0.025 (text / image / video)" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": "Gemini pricing may vary by modality and prompt length; this entry records the cited standard text or text/image/video tier.", "permalink": "/models/google/gemini-3_1-flash-lite.html" }, { "provider": "google", "model_id": "gemini-3.1-pro-preview", "display_name": "Gemini 3.1 Pro Preview", "status": "preview", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 2.0, "output_per_mtok": 12.0, "cached_input_per_mtok": 0.2, "batch_discount_pct": null }, "context_window_tokens": null, "max_output_tokens": null, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok", "modalities" ], "quote": "Gemini 3.1 Pro Preview `gemini-3.1-pro-preview` ... Input price Not available $2.00, prompts <= 200k tokens $4.00, prompts > 200k tokens Output price (including thinking tokens) Not available $12.00, prompts <= 200k tokens $18.00, prompts > 200k Context caching price Not available $0.20, prompts <= 200k tokens" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": "Gemini pricing may vary by modality and prompt length; this entry records the cited standard text or text/image/video tier.", "permalink": "/models/google/gemini-3_1-pro-preview.html" }, { "provider": "google", "model_id": "gemini-3.1-flash-live-preview", "display_name": "Gemini 3.1 Flash Live Preview", "status": "preview", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.75, "output_per_mtok": 4.5, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": null, "max_output_tokens": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "modalities" ], "quote": "Gemini 3.1 Flash Live Preview `gemini-3.1-flash-live-preview` ... Input price Free of charge $0.75 (text) $3.00 or $0.005/min (audio) $1.00 or $0.002/min (image/video) Output price (including thinking tokens) Free of charge $4.50 (text) $12.00 or $0.018/min (audio)" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": "Gemini pricing may vary by modality and prompt length; this entry records the cited standard text or text/image/video tier.", "permalink": "/models/google/gemini-3_1-flash-live-preview.html" }, { "provider": "google", "model_id": "gemini-3-flash-preview", "display_name": "Gemini 3 Flash Preview", "status": "preview", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.5, "output_per_mtok": 3.0, "cached_input_per_mtok": 0.05, "batch_discount_pct": null }, "context_window_tokens": null, "max_output_tokens": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok", "modalities" ], "quote": "Gemini 3 Flash Preview `gemini-3-flash-preview` ... Input price Free of charge $0.50 (text / image / video) $1.00 (audio) Output price (including thinking tokens) Free of charge $3.00 Context caching price Free of charge $0.05 (text / image / video)" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": "Gemini pricing may vary by modality and prompt length; this entry records the cited standard text or text/image/video tier.", "permalink": "/models/google/gemini-3-flash-preview.html" }, { "provider": "google", "model_id": "gemini-2.5-pro", "display_name": "Gemini 2.5 Pro", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 1.25, "output_per_mtok": 10.0, "cached_input_per_mtok": 0.125, "batch_discount_pct": null }, "context_window_tokens": null, "max_output_tokens": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok", "modalities" ], "quote": "Gemini 2.5 Pro `gemini-2.5-pro` ... Input price Free of charge $1.25, prompts <= 200k tokens $2.50, prompts > 200k tokens Output price (including thinking tokens) Free of charge $10.00, prompts <= 200k tokens $15.00, prompts > 200k Context caching price Not available $0.125, prompts <= 200k tokens" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": "Gemini pricing may vary by modality and prompt length; this entry records the cited standard text or text/image/video tier.", "permalink": "/models/google/gemini-2_5-pro.html" }, { "provider": "google", "model_id": "gemini-2.5-flash", "display_name": "Gemini 2.5 Flash", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.3, "output_per_mtok": 2.5, "cached_input_per_mtok": 0.03, "batch_discount_pct": null }, "context_window_tokens": 1048576, "max_output_tokens": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok", "modalities" ], "quote": "Gemini 2.5 Flash `gemini-2.5-flash` Our first hybrid reasoning model which supports a 1M token context window ... Input price Free of charge $0.30 (text / image / video) $1.00 (audio) Output price (including thinking tokens) Free of charge $2.50 Context caching price Not available $0.03 (text / image / video)" }, { "url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash", "accessed_at": "2026-07-04T07:37:12Z", "fields": [ "context_window_tokens" ], "quote": "Gemini 2.5 Flash ... Model code gemini-2.5-flash ... Token limits ... Input token limit 1,048,576 Output token limit 65,536" } ], "verified_at": "2026-07-04T07:37:12Z", "notes": "Gemini pricing may vary by modality and prompt length; this entry records the cited standard text or text/image/video tier.", "permalink": "/models/google/gemini-2_5-flash.html" }, { "provider": "google", "model_id": "gemini-2.5-flash-lite", "display_name": "Gemini 2.5 Flash-Lite", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.1, "output_per_mtok": 0.4, "cached_input_per_mtok": 0.01, "batch_discount_pct": null }, "context_window_tokens": null, "max_output_tokens": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok", "modalities" ], "quote": "Gemini 2.5 Flash-Lite `gemini-2.5-flash-lite` ... Input price (text, image, video) Free of charge $0.10 (text / image / video) $0.30 (audio) Output price (including thinking tokens) Free of charge $0.40 Context caching price Not available $0.01 (text / image / video)" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": "Gemini pricing may vary by modality and prompt length; this entry records the cited standard text or text/image/video tier.", "permalink": "/models/google/gemini-2_5-flash-lite.html" }, { "provider": "google", "model_id": "gemini-2.5-flash-lite-preview-09-2025", "display_name": "Gemini 2.5 Flash-Lite Preview", "status": "preview", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.1, "output_per_mtok": 0.4, "cached_input_per_mtok": 0.01, "batch_discount_pct": null }, "context_window_tokens": null, "max_output_tokens": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok", "modalities" ], "quote": "Gemini 2.5 Flash-Lite Preview `gemini-2.5-flash-lite-preview-09-2025` ... Input price (text, image, video) Free of charge $0.10 (text / image / video) $0.30 (audio) Output price (including thinking tokens) Free of charge $0.40 Context caching price Not available $0.01 (text / image / video)" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": "Gemini pricing may vary by modality and prompt length; this entry records the cited standard text or text/image/video tier.", "permalink": "/models/google/gemini-2_5-flash-lite-preview-09-2025.html" }, { "provider": "google", "model_id": "gemini-2.5-flash-native-audio-preview-12-2025", "display_name": "Gemini 2.5 Flash Native Audio", "status": "preview", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.5, "output_per_mtok": 2.0, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": null, "max_output_tokens": null, "modalities": { "input": [ "text", "audio", "video" ], "output": [ "text", "audio" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "modalities" ], "quote": "Gemini 2.5 Flash Native Audio (Live API) `gemini-2.5-flash-native-audio-preview-12-2025` ... Input price Free of charge $0.50 (text) $3.00 (audio / video) Output price (including thinking tokens) Free of charge $2.00 (text) $12.00 (audio)" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": "Gemini pricing may vary by modality and prompt length; this entry records the cited standard text or text/image/video tier.", "permalink": "/models/google/gemini-2_5-flash-native-audio-preview-12-2025.html" }, { "provider": "google", "model_id": "gemini-2.5-flash-preview-tts", "display_name": "Gemini 2.5 Flash Preview TTS", "status": "preview", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.5, "output_per_mtok": 10.0, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": null, "max_output_tokens": null, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://ai.google.dev/gemini-api/docs/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "modalities" ], "quote": "Gemini 2.5 Flash Preview TTS `gemini-2.5-flash-preview-tts` ... Input price Free of charge $0.50 (text) Output price Free of charge $10.00 (audio)" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": "Gemini pricing may vary by modality and prompt length; this entry records the cited standard text or text/image/video tier.", "permalink": "/models/google/gemini-2_5-flash-preview-tts.html" }, { "provider": "mistral", "model_id": "mistral-medium-latest", "display_name": "Mistral Medium 3.5", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 1.5, "output_per_mtok": 7.5, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": null, "max_output_tokens": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://mistral.ai/pricing/api/", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "modalities" ], "quote": "Mistral Medium 3.5 ... Text-to-text Reasoning Coding Agentic Multimodal Input (/M tokens) $1.5 Output (/M tokens) $7.5 mistral-medium-latest" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": null, "permalink": "/models/mistral/mistral-medium-latest.html" }, { "provider": "mistral", "model_id": "mistral-small-latest", "display_name": "Mistral Small 4", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.15, "output_per_mtok": 0.6, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": null, "max_output_tokens": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://mistral.ai/pricing/api/", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "modalities" ], "quote": "Mistral Small 4 ... Text-to-text Agentic Multimodal Lightweight Input (/M tokens) $0.15 Output (/M tokens) $0.6 mistral-small-latest" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": null, "permalink": "/models/mistral/mistral-small-latest.html" }, { "provider": "mistral", "model_id": "mistral-large-latest", "display_name": "Mistral Large 3", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.5, "output_per_mtok": 1.5, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": null, "max_output_tokens": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://mistral.ai/pricing/api/", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "modalities" ], "quote": "Mistral Large 3 ... Text-to-text Multimodal Input (/M tokens) $0.5 Output (/M tokens) $1.5 mistral-large-latest" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": null, "permalink": "/models/mistral/mistral-large-latest.html" }, { "provider": "mistral", "model_id": "voxtral-small-latest", "display_name": "Voxtral Small", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.1, "output_per_mtok": 0.4, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": null, "max_output_tokens": null, "modalities": { "input": [ "text", "audio" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://mistral.ai/pricing/api/", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "modalities" ], "quote": "Voxtral Small ... Audio Input (per min / per M tok) $0.004 Text Input (per min / per M tok) $0.1 Output (/M tokens) $0.4 Available on `/v1/chat/completions` voxtral-small-latest" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": null, "permalink": "/models/mistral/voxtral-small-latest.html" }, { "provider": "mistral", "model_id": "devstral-medium-latest", "display_name": "Devstral 2", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.4, "output_per_mtok": 2.0, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": null, "max_output_tokens": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://mistral.ai/pricing/api/", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "modalities" ], "quote": "Devstral 2 ... Coding Agentic Text-to-text Input (/M tokens) $0.4 Output (/M tokens) $2 devstral-medium-latest" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": null, "permalink": "/models/mistral/devstral-medium-latest.html" }, { "provider": "mistral", "model_id": "devstral-small-latest", "display_name": "Devstral Small 2", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.1, "output_per_mtok": 0.3, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": null, "max_output_tokens": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://mistral.ai/pricing/api/", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "modalities" ], "quote": "Devstral Small 2 ... Coding Agentic Text-to-text Lightweight Multimodal Input (/M tokens) $0.1 Output (/M tokens) $0.3 devstral-small-latest" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": null, "permalink": "/models/mistral/devstral-small-latest.html" }, { "provider": "mistral", "model_id": "codestral-latest", "display_name": "Codestral", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.3, "output_per_mtok": 0.9, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": null, "max_output_tokens": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://mistral.ai/pricing/api/", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "modalities" ], "quote": "Codestral ... Coding Text-to-text Input (/M tokens) $0.3 Output (/M tokens) $0.9 codestral-latest" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": null, "permalink": "/models/mistral/codestral-latest.html" }, { "provider": "mistral", "model_id": "magistral-medium-latest", "display_name": "Magistral Medium", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 2.0, "output_per_mtok": 5.0, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": null, "max_output_tokens": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://mistral.ai/pricing/api/", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "modalities" ], "quote": "Magistral Medium ... Text-to-text Reasoning Multimodal Input (/M tokens) $2 Output (/M tokens) $5 magistral-medium-latest" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": null, "permalink": "/models/mistral/magistral-medium-latest.html" }, { "provider": "xai", "model_id": "grok-build-0.1", "display_name": "Grok Build 0.1", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 1.0, "output_per_mtok": 2.0, "cached_input_per_mtok": 0.2, "batch_discount_pct": null }, "context_window_tokens": 256000, "context_window_notation": "256k", "max_output_tokens": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://docs.x.ai/developers/pricing", "accessed_at": "2026-07-04T06:08:18Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok", "context_window_tokens" ], "quote": "Chat API Prices per 1M tokens Model Context Input Cached input Output grok-build-0.1 256k$1.00$0.20$2.00 grok-4.3 1M$1.25$0.20$2.50 grok-4.20-multi-agent-0309 1M$1.25$0.20$2.50 grok-4.20-0309-reasoning 1M$1.25$0.20$2.50 grok-4.20-0309-non-reasoning 1M$1.25$0.20$2.50" }, { "url": "https://docs.x.ai/developers/models", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "modalities" ], "quote": "We have dedicated models and APIs for audio, image, and video capabilities. For everything else, use Grok 4.3." } ], "verified_at": "2026-07-04T06:08:18Z", "notes": null, "permalink": "/models/xai/grok-build-0_1.html" }, { "provider": "xai", "model_id": "grok-4.3", "display_name": "Grok 4.3", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 1.25, "output_per_mtok": 2.5, "cached_input_per_mtok": 0.2, "batch_discount_pct": null }, "context_window_tokens": 1000000, "context_window_notation": "1M", "max_output_tokens": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://docs.x.ai/developers/pricing", "accessed_at": "2026-07-04T06:08:18Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok", "context_window_tokens" ], "quote": "Chat API Prices per 1M tokens Model Context Input Cached input Output grok-build-0.1 256k$1.00$0.20$2.00 grok-4.3 1M$1.25$0.20$2.50 grok-4.20-multi-agent-0309 1M$1.25$0.20$2.50 grok-4.20-0309-reasoning 1M$1.25$0.20$2.50 grok-4.20-0309-non-reasoning 1M$1.25$0.20$2.50" }, { "url": "https://docs.x.ai/developers/models", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "modalities" ], "quote": "We have dedicated models and APIs for audio, image, and video capabilities. For everything else, use Grok 4.3." } ], "verified_at": "2026-07-04T06:08:18Z", "notes": null, "permalink": "/models/xai/grok-4_3.html" }, { "provider": "xai", "model_id": "grok-4.20-multi-agent-0309", "display_name": "Grok 4.20 Multi-Agent 0309", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 1.25, "output_per_mtok": 2.5, "cached_input_per_mtok": 0.2, "batch_discount_pct": null }, "context_window_tokens": 1000000, "context_window_notation": "1M", "max_output_tokens": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://docs.x.ai/developers/pricing", "accessed_at": "2026-07-04T06:08:18Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok", "context_window_tokens" ], "quote": "Chat API Prices per 1M tokens Model Context Input Cached input Output grok-build-0.1 256k$1.00$0.20$2.00 grok-4.3 1M$1.25$0.20$2.50 grok-4.20-multi-agent-0309 1M$1.25$0.20$2.50 grok-4.20-0309-reasoning 1M$1.25$0.20$2.50 grok-4.20-0309-non-reasoning 1M$1.25$0.20$2.50" }, { "url": "https://docs.x.ai/developers/models", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "modalities" ], "quote": "We have dedicated models and APIs for audio, image, and video capabilities. For everything else, use Grok 4.3." } ], "verified_at": "2026-07-04T06:08:18Z", "notes": null, "permalink": "/models/xai/grok-4_20-multi-agent-0309.html" }, { "provider": "xai", "model_id": "grok-4.20-0309-reasoning", "display_name": "Grok 4.20 0309 Reasoning", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 1.25, "output_per_mtok": 2.5, "cached_input_per_mtok": 0.2, "batch_discount_pct": null }, "context_window_tokens": 1000000, "context_window_notation": "1M", "max_output_tokens": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://docs.x.ai/developers/pricing", "accessed_at": "2026-07-04T06:08:18Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok", "context_window_tokens" ], "quote": "Chat API Prices per 1M tokens Model Context Input Cached input Output grok-build-0.1 256k$1.00$0.20$2.00 grok-4.3 1M$1.25$0.20$2.50 grok-4.20-multi-agent-0309 1M$1.25$0.20$2.50 grok-4.20-0309-reasoning 1M$1.25$0.20$2.50 grok-4.20-0309-non-reasoning 1M$1.25$0.20$2.50" }, { "url": "https://docs.x.ai/developers/models", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "modalities" ], "quote": "We have dedicated models and APIs for audio, image, and video capabilities. For everything else, use Grok 4.3." } ], "verified_at": "2026-07-04T06:08:18Z", "notes": null, "permalink": "/models/xai/grok-4_20-0309-reasoning.html" }, { "provider": "xai", "model_id": "grok-4.20-0309-non-reasoning", "display_name": "Grok 4.20 0309 Non-Reasoning", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 1.25, "output_per_mtok": 2.5, "cached_input_per_mtok": 0.2, "batch_discount_pct": null }, "context_window_tokens": 1000000, "context_window_notation": "1M", "max_output_tokens": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://docs.x.ai/developers/pricing", "accessed_at": "2026-07-04T06:08:18Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok", "context_window_tokens" ], "quote": "Chat API Prices per 1M tokens Model Context Input Cached input Output grok-build-0.1 256k$1.00$0.20$2.00 grok-4.3 1M$1.25$0.20$2.50 grok-4.20-multi-agent-0309 1M$1.25$0.20$2.50 grok-4.20-0309-reasoning 1M$1.25$0.20$2.50 grok-4.20-0309-non-reasoning 1M$1.25$0.20$2.50" }, { "url": "https://docs.x.ai/developers/models", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "modalities" ], "quote": "We have dedicated models and APIs for audio, image, and video capabilities. For everything else, use Grok 4.3." } ], "verified_at": "2026-07-04T06:08:18Z", "notes": null, "permalink": "/models/xai/grok-4_20-0309-non-reasoning.html" }, { "provider": "deepseek", "model_id": "deepseek-v4-flash", "display_name": "DeepSeek V4 Flash", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.14, "output_per_mtok": 0.28, "cached_input_per_mtok": 0.0028, "batch_discount_pct": null }, "context_window_tokens": 1000000, "context_window_notation": "1M", "max_output_tokens": 384000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://api-docs.deepseek.com/quick_start/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok", "context_window_tokens", "max_output_tokens", "modalities" ], "quote": "MODEL deepseek-v4-flash(1)deepseek-v4-pro ... CONTEXT LENGTH 1M MAX OUTPUT MAXIMUM: 384K ... 1M INPUT TOKENS (CACHE HIT)$0.0028$0.003625 1M INPUT TOKENS (CACHE MISS)$0.14$0.435 1M OUTPUT TOKENS$0.28$0.87" }, { "url": "https://api-docs.deepseek.com/api/list-models", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "model_id" ], "quote": "\"id\": \"deepseek-v4-flash\" ... \"id\": \"deepseek-v4-pro\"" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": null, "permalink": "/models/deepseek/deepseek-v4-flash.html" }, { "provider": "deepseek", "model_id": "deepseek-v4-pro", "display_name": "DeepSeek V4 Pro", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.435, "output_per_mtok": 0.87, "cached_input_per_mtok": 0.003625, "batch_discount_pct": null }, "context_window_tokens": 1000000, "context_window_notation": "1M", "max_output_tokens": 384000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://api-docs.deepseek.com/quick_start/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok", "context_window_tokens", "max_output_tokens", "modalities" ], "quote": "MODEL deepseek-v4-flash(1)deepseek-v4-pro ... CONTEXT LENGTH 1M MAX OUTPUT MAXIMUM: 384K ... 1M INPUT TOKENS (CACHE HIT)$0.0028$0.003625 1M INPUT TOKENS (CACHE MISS)$0.14$0.435 1M OUTPUT TOKENS$0.28$0.87" }, { "url": "https://api-docs.deepseek.com/api/list-models", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "model_id" ], "quote": "\"id\": \"deepseek-v4-flash\" ... \"id\": \"deepseek-v4-pro\"" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": null, "permalink": "/models/deepseek/deepseek-v4-pro.html" }, { "provider": "cohere", "model_id": "command-r-plus-08-2024", "display_name": "Command R+ 08-2024", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 2.5, "output_per_mtok": 10.0, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": 128000, "context_window_notation": "128k", "max_output_tokens": 4000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://cohere.com/pricing", "accessed_at": "2026-07-04T06:08:18Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok" ], "quote": "Command R+ 08-2024 pricing is $2.50/1M tokens for input and $10.00/1M tokens for output" }, { "url": "https://docs.cohere.com/docs/models", "accessed_at": "2026-07-04T06:08:18Z", "fields": [ "model_id", "status", "modalities", "context_window_tokens", "max_output_tokens" ], "quote": "`command-r-plus-08-2024 `Live `command-r-plus-08-2024` is an update of the Command R+ model, delivered in August 2024. Find more information here Text 128k 4k" } ], "verified_at": "2026-07-04T06:08:18Z", "notes": "Listed as legacy on Cohere pricing page", "permalink": "/models/cohere/command-r-plus-08-2024.html" }, { "provider": "cohere", "model_id": "command-r-03-2024", "display_name": "Command R 03-2024", "status": "deprecated", "release_date": null, "deprecation_date": "2025-09-15", "retirement_date": null, "pricing": { "input_per_mtok": 0.5, "output_per_mtok": 1.5, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": 128000, "context_window_notation": "128k", "max_output_tokens": 4000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://cohere.com/pricing", "accessed_at": "2026-07-04T06:08:18Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok" ], "quote": "Command R 03-2024 pricing is $0.50/1M tokens for input and $1.50/1M tokens for output" }, { "url": "https://docs.cohere.com/docs/models", "accessed_at": "2026-07-04T06:08:18Z", "fields": [ "model_id", "status", "modalities", "context_window_tokens", "max_output_tokens", "deprecation_date" ], "quote": "`command-r-03-2024 `Deprecated Sept 15, 2025 Command R is an instruction-following conversational model that performs language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows like code generation, retrieval augmented generation (RAG), tool use, and agents.Text 128k 4k" } ], "verified_at": "2026-07-04T06:08:18Z", "notes": null, "permalink": "/models/cohere/command-r-03-2024.html" }, { "provider": "cohere", "model_id": "command-r-plus-04-2024", "display_name": "Command R+ 04-2024", "status": "deprecated", "release_date": null, "deprecation_date": "2025-09-15", "retirement_date": null, "pricing": { "input_per_mtok": 3.0, "output_per_mtok": 15.0, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": 128000, "context_window_notation": "128k", "max_output_tokens": 4000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://cohere.com/pricing", "accessed_at": "2026-07-04T06:08:18Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok" ], "quote": "Command R+ 04-2024 pricing is $3.00/1M tokens for input and $15.00/1M tokens for output" }, { "url": "https://docs.cohere.com/docs/models", "accessed_at": "2026-07-04T06:08:18Z", "fields": [ "model_id", "status", "modalities", "context_window_tokens", "max_output_tokens", "deprecation_date" ], "quote": "`command-r-plus-04-2024 `Deprecated Sept 15, 2025 Command R+ is an instruction-following conversational model that performs language tasks at a higher quality, more reliably, and with a longer context than previous models. It is best suited for complex RAG workflows and multi-step tool use.Text 128k 4k" } ], "verified_at": "2026-07-04T06:08:18Z", "notes": null, "permalink": "/models/cohere/command-r-plus-04-2024.html" }, { "provider": "cohere", "model_id": "command", "display_name": "Command", "status": "deprecated", "release_date": null, "deprecation_date": "2025-09-15", "retirement_date": null, "pricing": { "input_per_mtok": 1.0, "output_per_mtok": 2.0, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": 4000, "context_window_notation": "4k", "max_output_tokens": 4000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://cohere.com/pricing", "accessed_at": "2026-07-04T06:08:18Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok" ], "quote": "Command pricing is $1.00/1M tokens for input and $2.00/1M tokens for output" }, { "url": "https://docs.cohere.com/docs/models", "accessed_at": "2026-07-04T06:08:18Z", "fields": [ "model_id", "status", "modalities", "context_window_tokens", "max_output_tokens", "deprecation_date" ], "quote": "`command `Deprecated Sept 15, 2025 An instruction-following conversational model that performs language tasks with high quality, more reliably and with a longer context than our base generative models.Text 4k 4k" } ], "verified_at": "2026-07-04T06:08:18Z", "notes": null, "permalink": "/models/cohere/command.html" }, { "provider": "cohere", "model_id": "command-light", "display_name": "Command Light", "status": "deprecated", "release_date": null, "deprecation_date": "2025-09-15", "retirement_date": null, "pricing": { "input_per_mtok": 0.3, "output_per_mtok": 0.6, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": 4000, "context_window_notation": "4k", "max_output_tokens": 4000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://cohere.com/pricing", "accessed_at": "2026-07-04T06:08:18Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok" ], "quote": "Command-light pricing is $0.30/1M tokens for input and $0.60/1M tokens for output" }, { "url": "https://docs.cohere.com/docs/models", "accessed_at": "2026-07-04T06:08:18Z", "fields": [ "model_id", "status", "modalities", "context_window_tokens", "max_output_tokens", "deprecation_date" ], "quote": "`command-light `Deprecated Sept 15, 2025 A smaller, faster version of `command`. Almost as capable, but a lot faster.Text 4k 4k" } ], "verified_at": "2026-07-04T06:08:18Z", "notes": null, "permalink": "/models/cohere/command-light.html" }, { "provider": "cohere", "model_id": "c4ai-aya-expanse-32b", "display_name": "Aya Expanse 32B", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.5, "output_per_mtok": 1.5, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": 128000, "context_window_notation": "128k", "max_output_tokens": 4000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://cohere.com/pricing", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok" ], "quote": "Aya Expanse models (8B and 32B) on the API are charged at $0.50/1M tokens for input and $1.50/1M tokens for output." }, { "url": "https://docs.cohere.com/docs/models", "accessed_at": "2026-07-04T05:55:32Z", "fields": [ "model_id", "status", "modalities", "context_window_tokens", "max_output_tokens" ], "quote": "`c4ai-aya-expanse-32b `Live Aya Expanse is a highly performant 32B multilingual model ... Text 128k 4k" } ], "verified_at": "2026-07-04T05:55:32Z", "notes": null, "permalink": "/models/cohere/c4ai-aya-expanse-32b.html" }, { "provider": "amazon", "model_id": "amazon.nova-premier-v1:0", "display_name": "Amazon Nova Premier", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 2.5, "output_per_mtok": 12.5, "cached_input_per_mtok": 0.625, "batch_discount_pct": null }, "context_window_tokens": 1000000, "context_window_notation": "1M", "max_output_tokens": 10000, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://aws.amazon.com/bedrock/pricing/", "accessed_at": "2026-07-04T08:00:00Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok" ], "quote": "Amazon Nova Premier $2.50 per 1M input tokens $12.50 per 1M output tokens; prompt cache read $0.625 per 1M tokens in us-east-1 on-demand." }, { "url": "https://docs.aws.amazon.com/nova/latest/userguide/what-is-nova.html", "accessed_at": "2026-07-04T08:00:00Z", "fields": [ "model_id", "modalities", "context_window_tokens", "max_output_tokens" ], "quote": "Model ID amazon.nova-premier-v1:0 amazon.nova-pro-v1:0 amazon.nova-lite-v1:0 amazon.nova-micro-v1:0 ... Input modalities Text, Image, Video Text, Image, Video Text, Image, Video Text ... Output Modalities Text Text Text Text ... Context Window 1M 300k 300k 128k ... Max Output Tokens 10K 10k 10k 10k" } ], "verified_at": "2026-07-04T08:00:00Z", "notes": "AWS Bedrock us-east-1 on-demand Standard tier; price table exposed on AWS Bedrock pricing.", "permalink": "/models/amazon/amazon_nova-premier-v1_0.html" }, { "provider": "amazon", "model_id": "amazon.nova-pro-v1:0", "display_name": "Amazon Nova Pro", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.8, "output_per_mtok": 3.2, "cached_input_per_mtok": 0.2, "batch_discount_pct": null }, "context_window_tokens": 300000, "context_window_notation": "300k", "max_output_tokens": 10000, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://aws.amazon.com/bedrock/pricing/", "accessed_at": "2026-07-04T08:00:00Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok" ], "quote": "Amazon Nova Pro $0.80 per 1M input tokens $3.20 per 1M output tokens; prompt cache read $0.20 per 1M tokens in us-east-1 on-demand." }, { "url": "https://docs.aws.amazon.com/nova/latest/userguide/what-is-nova.html", "accessed_at": "2026-07-04T08:00:00Z", "fields": [ "model_id", "modalities", "context_window_tokens", "max_output_tokens" ], "quote": "Model ID amazon.nova-premier-v1:0 amazon.nova-pro-v1:0 amazon.nova-lite-v1:0 amazon.nova-micro-v1:0 ... Input modalities Text, Image, Video Text, Image, Video Text, Image, Video Text ... Output Modalities Text Text Text Text ... Context Window 1M 300k 300k 128k ... Max Output Tokens 10K 10k 10k 10k" } ], "verified_at": "2026-07-04T08:00:00Z", "notes": "AWS Bedrock us-east-1 on-demand Standard tier; price table exposed on AWS Bedrock pricing.", "permalink": "/models/amazon/amazon_nova-pro-v1_0.html" }, { "provider": "amazon", "model_id": "amazon.nova-lite-v1:0", "display_name": "Amazon Nova Lite", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.06, "output_per_mtok": 0.24, "cached_input_per_mtok": 0.015, "batch_discount_pct": null }, "context_window_tokens": 300000, "context_window_notation": "300k", "max_output_tokens": 10000, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://aws.amazon.com/bedrock/pricing/", "accessed_at": "2026-07-04T08:00:00Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok" ], "quote": "Amazon Nova Lite $0.06 per 1M input tokens $0.24 per 1M output tokens; prompt cache read $0.015 per 1M tokens in us-east-1 on-demand." }, { "url": "https://docs.aws.amazon.com/nova/latest/userguide/what-is-nova.html", "accessed_at": "2026-07-04T08:00:00Z", "fields": [ "model_id", "modalities", "context_window_tokens", "max_output_tokens" ], "quote": "Model ID amazon.nova-premier-v1:0 amazon.nova-pro-v1:0 amazon.nova-lite-v1:0 amazon.nova-micro-v1:0 ... Input modalities Text, Image, Video Text, Image, Video Text, Image, Video Text ... Output Modalities Text Text Text Text ... Context Window 1M 300k 300k 128k ... Max Output Tokens 10K 10k 10k 10k" } ], "verified_at": "2026-07-04T08:00:00Z", "notes": "AWS Bedrock us-east-1 on-demand Standard tier; price table exposed on AWS Bedrock pricing.", "permalink": "/models/amazon/amazon_nova-lite-v1_0.html" }, { "provider": "amazon", "model_id": "amazon.nova-micro-v1:0", "display_name": "Amazon Nova Micro", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.035, "output_per_mtok": 0.14, "cached_input_per_mtok": 0.00875, "batch_discount_pct": null }, "context_window_tokens": 128000, "context_window_notation": "128k", "max_output_tokens": 10000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://aws.amazon.com/bedrock/pricing/", "accessed_at": "2026-07-04T08:00:00Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok" ], "quote": "Amazon Nova Micro $0.035 per 1M input tokens $0.14 per 1M output tokens; prompt cache read $0.00875 per 1M tokens in us-east-1 on-demand." }, { "url": "https://docs.aws.amazon.com/nova/latest/userguide/what-is-nova.html", "accessed_at": "2026-07-04T08:00:00Z", "fields": [ "model_id", "modalities", "context_window_tokens", "max_output_tokens" ], "quote": "Model ID amazon.nova-premier-v1:0 amazon.nova-pro-v1:0 amazon.nova-lite-v1:0 amazon.nova-micro-v1:0 ... Input modalities Text, Image, Video Text, Image, Video Text, Image, Video Text ... Output Modalities Text Text Text Text ... Context Window 1M 300k 300k 128k ... Max Output Tokens 10K 10k 10k 10k" } ], "verified_at": "2026-07-04T08:00:00Z", "notes": "AWS Bedrock us-east-1 on-demand Standard tier; price table exposed on AWS Bedrock pricing.", "permalink": "/models/amazon/amazon_nova-micro-v1_0.html" }, { "provider": "alibaba", "model_id": "qwen3.7-max", "display_name": "Qwen3.7 Max", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 2.5, "output_per_mtok": 7.5, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": 1000000, "context_window_notation": "1M", "max_output_tokens": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "accessed_at": "2026-07-04T08:00:00Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "context_window_tokens" ], "quote": "Model ID ... qwen3.7-max International Non-Thinking and Thinking modes 0 Qwen3.7: Model ID qwen3.7-plus; Input Text, images, video; Output Text; Context 1M; Max output 64k." } ], "verified_at": "2026-07-04T08:44:47Z", "notes": "International/Global Model Studio price; base 0 Qwen3.7: Model ID qwen3.7-plus-2026-05-26; Input Text, images, video; Output Text; Context 1M; Max output 64k." } ], "verified_at": "2026-07-04T08:44:47Z", "notes": "International/Global Model Studio price; base 0 Qwen3.6: Model ID qwen3.6-plus; Input Text, images, video; Output Text; Context 1M; Max output 64k." } ], "verified_at": "2026-07-04T08:44:47Z", "notes": "International/Global Model Studio price; base 0 Qwen3.6: Model ID qwen3.6-plus-2026-04-02; Input Text, images, video; Output Text; Context 1M; Max output 64k." } ], "verified_at": "2026-07-04T08:44:47Z", "notes": "International/Global Model Studio price; base 0 Qwen3.6: Model ID qwen3.6-flash; Input Text, images, video; Output Text; Context 1M; Max output 64k." } ], "verified_at": "2026-07-04T08:44:47Z", "notes": "International Model Studio price; 0 Qwen3.6: Model ID qwen3.6-flash-2026-04-16; Input Text, images, video; Output Text; Context 1M; Max output 64k." } ], "verified_at": "2026-07-04T08:44:47Z", "notes": "International Model Studio price; 016B serverless token tier recorded.", "permalink": "/models/fireworks/llama-v3p3-70b-instruct.html" }, { "provider": "fireworks", "model_id": "qwen2p5-vl-32b-instruct", "display_name": "Qwen2.5-VL 32B Instruct", "status": "ga", "release_date": null, "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.9, "output_per_mtok": 0.9, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": 128000, "max_output_tokens": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://docs.fireworks.ai/serverless/pricing", "accessed_at": "2026-07-04T08:44:47Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok" ], "quote": "Prices below are per 1 million tokens in US dollars ... Other base models -- by size and architecture ... More than 16B parameters $0.90" }, { "url": "https://fireworks.ai/models/fireworks/qwen2p5-vl-32b-instruct", "accessed_at": "2026-07-04T08:44:47Z", "fields": [ "model_id", "context_window_tokens", "modalities" ], "quote": "model path:accounts/fireworks/models/qwen2p5-vl-32b-instruct ... Fireworks supports up to 128,000 tokens ... The model is supported on serverless deployment at $0.90 per million tokens ... Support image input Supported" } ], "verified_at": "2026-07-04T08:44:47Z", "notes": "Provider is Fireworks serving platform; upstream model family is Qwen. Generic >16B serverless token tier recorded.", "permalink": "/models/fireworks/qwen2p5-vl-32b-instruct.html" }, { "provider": "together", "model_id": "Qwen/Qwen2.5-7B-Instruct-Turbo", "display_name": "Qwen2.5 7B Instruct Turbo", "status": "ga", "release_date": "2024-10-11", "deprecation_date": null, "retirement_date": null, "pricing": { "input_per_mtok": 0.3, "output_per_mtok": 0.3, "cached_input_per_mtok": null, "batch_discount_pct": null }, "context_window_tokens": 32768, "context_window_notation": "32K", "max_output_tokens": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://www.together.ai/pricing", "accessed_at": "2026-07-04T08:44:47Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok" ], "quote": "Qwen2.5 7B Instruct Turbo $0.30 $0.30 ... Displayed prices refer to the lowest resolution/duration settings. Price per 1M tokens" }, { "url": "https://www.together.ai/models/qwen2-5-7b-instruct-turbo", "accessed_at": "2026-07-04T08:44:47Z", "fields": [ "model_id", "context_window_tokens", "modalities", "release_date" ], "quote": "Endpoint: Qwen/Qwen2.5-7B-Instruct-Turbo ... Context length 32K ... Input modalities Text Output modalities Text Released October 11, 2024" } ], "verified_at": "2026-07-04T08:44:47Z", "notes": "Provider is Together AI serving platform; exact endpoint ID recorded from Together model page.", "permalink": "/models/together/Qwen_Qwen2_5-7B-Instruct-Turbo.html" }, { "provider": "amazon", "model_id": "anthropic.claude-3-5-sonnet-20241022-v2:0", "display_name": "Anthropic Claude 3.5 Sonnet v2 on Bedrock", "status": "deprecated", "release_date": null, "deprecation_date": "2026-01-30", "retirement_date": "2026-07-30", "pricing": { "input_per_mtok": 6.0, "output_per_mtok": 30.0, "cached_input_per_mtok": 0.6, "batch_discount_pct": null }, "context_window_tokens": 200000, "context_window_notation": "200K", "max_output_tokens": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "knowledge_cutoff": null, "sources": [ { "url": "https://aws.amazon.com/bedrock/pricing/", "accessed_at": "2026-07-04T08:44:47Z", "fields": [ "pricing.input_per_mtok", "pricing.output_per_mtok", "pricing.cached_input_per_mtok" ], "quote": "Anthropic Claude 3.5 Sonnet v2 (Public Extended Access, Effective 1 Dec 2025) ... $6.00 $30.00 $3.00 $15.00 $7.50 $0.60" }, { "url": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle.html", "accessed_at": "2026-07-04T08:44:47Z", "fields": [ "model_id", "status", "deprecation_date", "retirement_date" ], "quote": "Claude 3.5 Sonnet v2 anthropic.claude-3-5-sonnet-20241022-v2:0 ... Legacy date January 30, 2026 EOL date July 30, 2026 Public extended access start date April 30, 2026" }, { "url": "https://www.anthropic.com/news/claude-3-5-sonnet", "accessed_at": "2026-07-04T08:44:47Z", "fields": [ "context_window_tokens", "modalities" ], "quote": "Claude 3.5 Sonnet is now available ... via Anthropic API, Amazon Bedrock, and Google Cloud Vertex AI ... 200K token context window ... vision capabilities" } ], "verified_at": "2026-07-04T08:44:47Z", "notes": "hosted third-party model (Anthropic) on Bedrock; Public Extended Access price recorded from AWS Bedrock pricing.", "permalink": "/models/amazon/anthropic_claude-3-5-sonnet-20241022-v2_0.html" } ] }