{"schemaVersion":"2.0","name":"PayAPIKey AI model pricing reference","description":"First-party sourced model prices used by the PayAPIKey AI Model Cost Calculator. Verify the linked provider sources before a billing decision.","currency":"USD","units":{"tokenRates":"USD per 1M tokens","cacheStorage":"USD per 1M cached tokens per hour"},"verifiedAt":"2026-08-03","methodologyUrl":"https://www.payapikey.com/methodology","calculatorUrl":"https://www.payapikey.com/tools/ai-model-cost-calculator","license":"https://creativecommons.org/licenses/by/4.0/","sourcePolicy":"Only first-party provider pricing and model documentation is used; provider-specific prices are not inferred.","optionalRateSemantics":"An absent optional rate means not separately published; it is not a zero price. The calculator uses the selected tier input rate when cachedInputRate is absent and discloses standard-price fallback when batch pricing is absent.","modelCount":50,"models":[{"id":"openai-gpt-5.6-sol","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"OpenAI","display":"GPT-5.6 Sol","modelId":"gpt-5.6-sol","lifecycleStatus":"ga","note":"Official standard and batch token rates; unpublished price components remain absent. Rates above 272k prompt tokens use the long-context tier.","standard":{"inputRate":5,"cachedInputRate":0.5,"cacheWriteRate":6.25,"outputRate":30},"batch":{"inputRate":2.5,"cachedInputRate":0.25,"cacheWriteRate":3.125,"outputRate":15},"longContext":{"thresholdTokens":272000,"operator":"gt","standard":{"inputRate":10,"cachedInputRate":1,"cacheWriteRate":12.5,"outputRate":45},"batch":{"inputRate":5,"cachedInputRate":0.5,"cacheWriteRate":6.25,"outputRate":22.5}},"sourceUrls":["https://developers.openai.com/api/docs/pricing","https://developers.openai.com/api/docs/models/all"],"sourceLabel":"OpenAI API pricing and model documentation"},{"id":"openai-gpt-5.6-terra","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"OpenAI","display":"GPT-5.6 Terra","modelId":"gpt-5.6-terra","lifecycleStatus":"ga","note":"Official standard and batch token rates; unpublished price components remain absent. Rates above 272k prompt tokens use the long-context tier.","standard":{"inputRate":2,"cachedInputRate":0.2,"cacheWriteRate":2.5,"outputRate":12},"batch":{"inputRate":1,"cachedInputRate":0.1,"cacheWriteRate":1.25,"outputRate":6},"longContext":{"thresholdTokens":272000,"operator":"gt","standard":{"inputRate":4,"cachedInputRate":0.4,"cacheWriteRate":5,"outputRate":18},"batch":{"inputRate":2,"cachedInputRate":0.2,"cacheWriteRate":2.5,"outputRate":9}},"sourceUrls":["https://developers.openai.com/api/docs/pricing","https://developers.openai.com/api/docs/models/all"],"sourceLabel":"OpenAI API pricing and model documentation"},{"id":"openai-gpt-5.6-luna","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"OpenAI","display":"GPT-5.6 Luna","modelId":"gpt-5.6-luna","lifecycleStatus":"ga","note":"Official standard and batch token rates; unpublished price components remain absent. Rates above 272k prompt tokens use the long-context tier.","standard":{"inputRate":0.2,"cachedInputRate":0.02,"cacheWriteRate":0.25,"outputRate":1.2},"batch":{"inputRate":0.1,"cachedInputRate":0.01,"cacheWriteRate":0.125,"outputRate":0.6},"longContext":{"thresholdTokens":272000,"operator":"gt","standard":{"inputRate":0.4,"cachedInputRate":0.04,"cacheWriteRate":0.5,"outputRate":1.8},"batch":{"inputRate":0.2,"cachedInputRate":0.02,"cacheWriteRate":0.25,"outputRate":0.9}},"sourceUrls":["https://developers.openai.com/api/docs/pricing","https://developers.openai.com/api/docs/models/all"],"sourceLabel":"OpenAI API pricing and model documentation"},{"id":"openai-gpt-5.5","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"OpenAI","display":"GPT-5.5","modelId":"gpt-5.5","lifecycleStatus":"ga","note":"Official standard and batch token rates; unpublished price components remain absent. Rates above 272k prompt tokens use the long-context tier.","standard":{"inputRate":5,"cachedInputRate":0.5,"outputRate":30},"batch":{"inputRate":2.5,"cachedInputRate":0.25,"outputRate":15},"longContext":{"thresholdTokens":272000,"operator":"gt","standard":{"inputRate":10,"cachedInputRate":1,"outputRate":45},"batch":{"inputRate":5,"cachedInputRate":0.5,"outputRate":22.5}},"sourceUrls":["https://developers.openai.com/api/docs/pricing","https://developers.openai.com/api/docs/models/all"],"sourceLabel":"OpenAI API pricing and model documentation"},{"id":"openai-gpt-5.5-pro","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"OpenAI","display":"GPT-5.5 Pro","modelId":"gpt-5.5-pro","lifecycleStatus":"ga","note":"Official standard and batch token rates; unpublished price components remain absent. No long-context batch rate is published above 272k prompt tokens.","standard":{"inputRate":30,"outputRate":180},"batch":{"inputRate":15,"outputRate":90},"longContext":{"thresholdTokens":272000,"operator":"gt","standard":{"inputRate":60,"outputRate":270}},"sourceUrls":["https://developers.openai.com/api/docs/pricing","https://developers.openai.com/api/docs/models/all"],"sourceLabel":"OpenAI API pricing and model documentation"},{"id":"openai-gpt-5.4","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"OpenAI","display":"GPT-5.4","modelId":"gpt-5.4","lifecycleStatus":"ga","note":"Official standard and batch token rates; unpublished price components remain absent. Rates above 272k prompt tokens use the long-context tier.","standard":{"inputRate":2.5,"cachedInputRate":0.25,"outputRate":15},"batch":{"inputRate":1.25,"cachedInputRate":0.13,"outputRate":7.5},"longContext":{"thresholdTokens":272000,"operator":"gt","standard":{"inputRate":5,"cachedInputRate":0.5,"outputRate":22.5},"batch":{"inputRate":2.5,"cachedInputRate":0.25,"outputRate":11.25}},"sourceUrls":["https://developers.openai.com/api/docs/pricing","https://developers.openai.com/api/docs/models/all"],"sourceLabel":"OpenAI API pricing and model documentation"},{"id":"openai-gpt-5.4-mini","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"OpenAI","display":"GPT-5.4 Mini","modelId":"gpt-5.4-mini","lifecycleStatus":"ga","note":"Official standard and batch token rates; unpublished price components remain absent.","standard":{"inputRate":0.75,"cachedInputRate":0.075,"outputRate":4.5},"batch":{"inputRate":0.375,"cachedInputRate":0.0375,"outputRate":2.25},"sourceUrls":["https://developers.openai.com/api/docs/pricing","https://developers.openai.com/api/docs/models/all"],"sourceLabel":"OpenAI API pricing and model documentation"},{"id":"openai-gpt-5.4-nano","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"OpenAI","display":"GPT-5.4 Nano","modelId":"gpt-5.4-nano","lifecycleStatus":"ga","note":"Official standard and batch token rates; unpublished price components remain absent.","standard":{"inputRate":0.2,"cachedInputRate":0.02,"outputRate":1.25},"batch":{"inputRate":0.1,"cachedInputRate":0.01,"outputRate":0.625},"sourceUrls":["https://developers.openai.com/api/docs/pricing","https://developers.openai.com/api/docs/models/all"],"sourceLabel":"OpenAI API pricing and model documentation"},{"id":"openai-gpt-5.4-pro","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"OpenAI","display":"GPT-5.4 Pro","modelId":"gpt-5.4-pro","lifecycleStatus":"ga","note":"Official standard and batch token rates; unpublished price components remain absent. Rates above 272k prompt tokens use the long-context tier.","standard":{"inputRate":30,"outputRate":180},"batch":{"inputRate":15,"outputRate":90},"longContext":{"thresholdTokens":272000,"operator":"gt","standard":{"inputRate":60,"outputRate":270},"batch":{"inputRate":30,"outputRate":135}},"sourceUrls":["https://developers.openai.com/api/docs/pricing","https://developers.openai.com/api/docs/models/all"],"sourceLabel":"OpenAI API pricing and model documentation"},{"id":"openai-gpt-5.2","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"OpenAI","display":"GPT-5.2","modelId":"gpt-5.2","lifecycleStatus":"legacy","note":"Official standard and batch token rates; unpublished price components remain absent. This served model is marked legacy, not retired.","standard":{"inputRate":1.75,"cachedInputRate":0.175,"outputRate":14},"batch":{"inputRate":0.875,"cachedInputRate":0.0875,"outputRate":7},"sourceUrls":["https://developers.openai.com/api/docs/pricing","https://developers.openai.com/api/docs/models/all","https://developers.openai.com/api/docs/deprecations"],"sourceLabel":"OpenAI API pricing and model documentation"},{"id":"openai-gpt-5.2-pro","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"OpenAI","display":"GPT-5.2 Pro","modelId":"gpt-5.2-pro","lifecycleStatus":"legacy","note":"Official standard and batch token rates; unpublished price components remain absent. This served model is marked legacy, not retired.","standard":{"inputRate":21,"outputRate":168},"batch":{"inputRate":10.5,"outputRate":84},"sourceUrls":["https://developers.openai.com/api/docs/pricing","https://developers.openai.com/api/docs/models/all","https://developers.openai.com/api/docs/deprecations"],"sourceLabel":"OpenAI API pricing and model documentation"},{"id":"openai-gpt-5.1","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"OpenAI","display":"GPT-5.1","modelId":"gpt-5.1","lifecycleStatus":"legacy","note":"Official standard and batch token rates; unpublished price components remain absent. This served model is marked legacy, not retired.","standard":{"inputRate":1.25,"cachedInputRate":0.125,"outputRate":10},"batch":{"inputRate":0.625,"cachedInputRate":0.0625,"outputRate":5},"sourceUrls":["https://developers.openai.com/api/docs/pricing","https://developers.openai.com/api/docs/models/all","https://developers.openai.com/api/docs/deprecations"],"sourceLabel":"OpenAI API pricing and model documentation"},{"id":"openai-gpt-4.1","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"OpenAI","display":"GPT-4.1","modelId":"gpt-4.1","lifecycleStatus":"legacy","note":"Official standard and batch token rates; unpublished price components remain absent. This served model is marked legacy, not retired.","standard":{"inputRate":2,"cachedInputRate":0.5,"outputRate":8},"batch":{"inputRate":1,"outputRate":4},"sourceUrls":["https://developers.openai.com/api/docs/pricing","https://developers.openai.com/api/docs/models/all","https://developers.openai.com/api/docs/deprecations"],"sourceLabel":"OpenAI API pricing and model documentation"},{"id":"openai-gpt-4.1-mini","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"OpenAI","display":"GPT-4.1 Mini","modelId":"gpt-4.1-mini","lifecycleStatus":"legacy","note":"Official standard and batch token rates; unpublished price components remain absent. This served model is marked legacy, not retired.","standard":{"inputRate":0.4,"cachedInputRate":0.1,"outputRate":1.6},"batch":{"inputRate":0.2,"outputRate":0.8},"sourceUrls":["https://developers.openai.com/api/docs/pricing","https://developers.openai.com/api/docs/models/all","https://developers.openai.com/api/docs/deprecations"],"sourceLabel":"OpenAI API pricing and model documentation"},{"id":"openai-gpt-4o","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"OpenAI","display":"GPT-4o","modelId":"gpt-4o","lifecycleStatus":"legacy","note":"Official standard and batch token rates; unpublished price components remain absent. This served model is marked legacy, not retired.","standard":{"inputRate":2.5,"cachedInputRate":1.25,"outputRate":10},"batch":{"inputRate":1.25,"outputRate":5},"sourceUrls":["https://developers.openai.com/api/docs/pricing","https://developers.openai.com/api/docs/models/all","https://developers.openai.com/api/docs/deprecations"],"sourceLabel":"OpenAI API pricing and model documentation"},{"id":"openai-gpt-4o-mini","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"OpenAI","display":"GPT-4o Mini","modelId":"gpt-4o-mini","lifecycleStatus":"legacy","note":"Official standard and batch token rates; unpublished price components remain absent. This served model is marked legacy, not retired.","standard":{"inputRate":0.15,"cachedInputRate":0.075,"outputRate":0.6},"batch":{"inputRate":0.075,"outputRate":0.3},"sourceUrls":["https://developers.openai.com/api/docs/pricing","https://developers.openai.com/api/docs/models/all","https://developers.openai.com/api/docs/deprecations"],"sourceLabel":"OpenAI API pricing and model documentation"},{"id":"anthropic-claude-fable-5","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Anthropic","display":"Claude Fable 5","modelId":"claude-fable-5","lifecycleStatus":"ga","contextWindowTokens":1000000,"note":"Official token rates with distinct cache-read, five-minute write, and one-hour write prices.","standard":{"inputRate":10,"cachedInputRate":1,"cacheWrite5mRate":12.5,"cacheWrite1hRate":20,"outputRate":50},"batch":{"inputRate":5,"outputRate":25},"sourceUrls":["https://platform.claude.com/docs/en/about-claude/pricing","https://platform.claude.com/docs/en/about-claude/models/overview"],"sourceLabel":"Anthropic Claude pricing and model documentation"},{"id":"anthropic-claude-opus-5","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Anthropic","display":"Claude Opus 5","modelId":"claude-opus-5","contextWindowTokens":1000000,"lifecycleStatus":"ga","note":"Official token rates with distinct cache-read, five-minute write, and one-hour write prices.","standard":{"inputRate":5,"cachedInputRate":0.5,"cacheWrite5mRate":6.25,"cacheWrite1hRate":10,"outputRate":25},"batch":{"inputRate":2.5,"outputRate":12.5},"sourceUrls":["https://platform.claude.com/docs/en/about-claude/pricing","https://platform.claude.com/docs/en/about-claude/models/overview"],"sourceLabel":"Anthropic Claude pricing and model documentation"},{"id":"anthropic-claude-opus-4-8","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Anthropic","display":"Claude Opus 4.8","modelId":"claude-opus-4-8","contextWindowTokens":1000000,"lifecycleStatus":"ga","note":"Official token rates with distinct cache-read, five-minute write, and one-hour write prices.","standard":{"inputRate":5,"cachedInputRate":0.5,"cacheWrite5mRate":6.25,"cacheWrite1hRate":10,"outputRate":25},"batch":{"inputRate":2.5,"outputRate":12.5},"sourceUrls":["https://platform.claude.com/docs/en/about-claude/pricing","https://platform.claude.com/docs/en/about-claude/models/overview"],"sourceLabel":"Anthropic Claude pricing and model documentation"},{"id":"anthropic-claude-opus-4-7","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Anthropic","display":"Claude Opus 4.7","modelId":"claude-opus-4-7","contextWindowTokens":1000000,"lifecycleStatus":"ga","note":"Official token rates with distinct cache-read, five-minute write, and one-hour write prices.","standard":{"inputRate":5,"cachedInputRate":0.5,"cacheWrite5mRate":6.25,"cacheWrite1hRate":10,"outputRate":25},"batch":{"inputRate":2.5,"outputRate":12.5},"sourceUrls":["https://platform.claude.com/docs/en/about-claude/pricing","https://platform.claude.com/docs/en/about-claude/models/overview"],"sourceLabel":"Anthropic Claude pricing and model documentation"},{"id":"anthropic-claude-opus-4-6","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Anthropic","display":"Claude Opus 4.6","modelId":"claude-opus-4-6","contextWindowTokens":1000000,"lifecycleStatus":"ga","note":"Official token rates with distinct cache-read, five-minute write, and one-hour write prices.","standard":{"inputRate":5,"cachedInputRate":0.5,"cacheWrite5mRate":6.25,"cacheWrite1hRate":10,"outputRate":25},"batch":{"inputRate":2.5,"outputRate":12.5},"sourceUrls":["https://platform.claude.com/docs/en/about-claude/pricing","https://platform.claude.com/docs/en/about-claude/models/overview"],"sourceLabel":"Anthropic Claude pricing and model documentation"},{"id":"anthropic-claude-opus-4-5-20251101","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Anthropic","display":"Claude Opus 4.5","modelId":"claude-opus-4-5-20251101","lifecycleStatus":"ga","note":"Official token rates with distinct cache-read, five-minute write, and one-hour write prices.","aliases":["claude-opus-4-5"],"standard":{"inputRate":5,"cachedInputRate":0.5,"cacheWrite5mRate":6.25,"cacheWrite1hRate":10,"outputRate":25},"batch":{"inputRate":2.5,"outputRate":12.5},"sourceUrls":["https://platform.claude.com/docs/en/about-claude/pricing","https://platform.claude.com/docs/en/about-claude/models/overview"],"sourceLabel":"Anthropic Claude pricing and model documentation"},{"id":"anthropic-claude-sonnet-5","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Anthropic","display":"Claude Sonnet 5","modelId":"claude-sonnet-5","lifecycleStatus":"ga","contextWindowTokens":1000000,"effectiveUntil":"2026-08-31","note":"Official token rates with distinct cache-read, five-minute write, and one-hour write prices. Introductory pricing ends after 2026-08-31.","standard":{"inputRate":2,"cachedInputRate":0.2,"cacheWrite5mRate":2.5,"cacheWrite1hRate":4,"outputRate":10},"batch":{"inputRate":1,"outputRate":5},"nextPricing":{"effectiveFrom":"2026-09-01","standard":{"inputRate":3,"cachedInputRate":0.3,"cacheWrite5mRate":3.75,"cacheWrite1hRate":6,"outputRate":15},"batch":{"inputRate":1.5,"outputRate":7.5}},"sourceUrls":["https://platform.claude.com/docs/en/about-claude/pricing","https://platform.claude.com/docs/en/about-claude/models/overview"],"sourceLabel":"Anthropic Claude pricing and model documentation"},{"id":"anthropic-claude-sonnet-4-6","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Anthropic","display":"Claude Sonnet 4.6","modelId":"claude-sonnet-4-6","lifecycleStatus":"ga","contextWindowTokens":1000000,"note":"Official token rates with distinct cache-read, five-minute write, and one-hour write prices.","standard":{"inputRate":3,"cachedInputRate":0.3,"cacheWrite5mRate":3.75,"cacheWrite1hRate":6,"outputRate":15},"batch":{"inputRate":1.5,"outputRate":7.5},"sourceUrls":["https://platform.claude.com/docs/en/about-claude/pricing","https://platform.claude.com/docs/en/about-claude/models/overview"],"sourceLabel":"Anthropic Claude pricing and model documentation"},{"id":"anthropic-claude-sonnet-4-5-20250929","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Anthropic","display":"Claude Sonnet 4.5","modelId":"claude-sonnet-4-5-20250929","lifecycleStatus":"ga","note":"Official token rates with distinct cache-read, five-minute write, and one-hour write prices.","aliases":["claude-sonnet-4-5"],"standard":{"inputRate":3,"cachedInputRate":0.3,"cacheWrite5mRate":3.75,"cacheWrite1hRate":6,"outputRate":15},"batch":{"inputRate":1.5,"outputRate":7.5},"sourceUrls":["https://platform.claude.com/docs/en/about-claude/pricing","https://platform.claude.com/docs/en/about-claude/models/overview"],"sourceLabel":"Anthropic Claude pricing and model documentation"},{"id":"anthropic-claude-haiku-4-5-20251001","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Anthropic","display":"Claude Haiku 4.5","modelId":"claude-haiku-4-5-20251001","lifecycleStatus":"ga","contextWindowTokens":200000,"note":"Official token rates with distinct cache-read, five-minute write, and one-hour write prices.","aliases":["claude-haiku-4-5"],"standard":{"inputRate":1,"cachedInputRate":0.1,"cacheWrite5mRate":1.25,"cacheWrite1hRate":2,"outputRate":5},"batch":{"inputRate":0.5,"outputRate":2.5},"sourceUrls":["https://platform.claude.com/docs/en/about-claude/pricing","https://platform.claude.com/docs/en/about-claude/models/overview"],"sourceLabel":"Anthropic Claude pricing and model documentation"},{"id":"google-gemini-3.6-flash","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Google","display":"Gemini 3.6 Flash","modelId":"gemini-3.6-flash","lifecycleStatus":"ga","note":"Official paid-tier text token rates; hourly context-cache storage is recorded separately.","standard":{"inputRate":1.5,"cachedInputRate":0.15,"outputRate":7.5},"batch":{"inputRate":0.75,"cachedInputRate":0.075,"outputRate":3.75},"cacheStorage":{"rate":1,"unit":"USD per 1M cached tokens per hour"},"sourceUrls":["https://ai.google.dev/gemini-api/docs/pricing","https://ai.google.dev/gemini-api/docs/models"],"sourceLabel":"Google Gemini API pricing and model documentation"},{"id":"google-gemini-3.5-flash","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Google","display":"Gemini 3.5 Flash","modelId":"gemini-3.5-flash","lifecycleStatus":"ga","note":"Official paid-tier text token rates; hourly context-cache storage is recorded separately.","standard":{"inputRate":1.5,"cachedInputRate":0.15,"outputRate":9},"batch":{"inputRate":0.75,"cachedInputRate":0.075,"outputRate":4.5},"cacheStorage":{"rate":1,"unit":"USD per 1M cached tokens per hour"},"sourceUrls":["https://ai.google.dev/gemini-api/docs/pricing","https://ai.google.dev/gemini-api/docs/models"],"sourceLabel":"Google Gemini API pricing and model documentation"},{"id":"google-gemini-3.5-flash-lite","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Google","display":"Gemini 3.5 Flash-Lite","modelId":"gemini-3.5-flash-lite","lifecycleStatus":"ga","note":"Official paid-tier text token rates; hourly context-cache storage is recorded separately.","standard":{"inputRate":0.3,"cachedInputRate":0.03,"outputRate":2.5},"batch":{"inputRate":0.15,"cachedInputRate":0.02,"outputRate":1.25},"cacheStorage":{"rate":1,"unit":"USD per 1M cached tokens per hour"},"sourceUrls":["https://ai.google.dev/gemini-api/docs/pricing","https://ai.google.dev/gemini-api/docs/models"],"sourceLabel":"Google Gemini API pricing and model documentation"},{"id":"google-gemini-3.1-flash-lite","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Google","display":"Gemini 3.1 Flash-Lite","modelId":"gemini-3.1-flash-lite","lifecycleStatus":"ga","note":"Official paid-tier text token rates; hourly context-cache storage is recorded separately.","standard":{"inputRate":0.25,"cachedInputRate":0.025,"outputRate":1.5},"batch":{"inputRate":0.125,"cachedInputRate":0.0125,"outputRate":0.75},"cacheStorage":{"rate":1,"unit":"USD per 1M cached tokens per hour"},"sourceUrls":["https://ai.google.dev/gemini-api/docs/pricing","https://ai.google.dev/gemini-api/docs/models"],"sourceLabel":"Google Gemini API pricing and model documentation"},{"id":"google-gemini-3.1-pro-preview","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Google","display":"Gemini 3.1 Pro Preview","modelId":"gemini-3.1-pro-preview","lifecycleStatus":"preview","note":"Official paid-tier text token rates; hourly context-cache storage is recorded separately. Rates above 200k prompt tokens use the long-context tier.","standard":{"inputRate":2,"cachedInputRate":0.2,"outputRate":12},"batch":{"inputRate":1,"cachedInputRate":0.2,"outputRate":6},"longContext":{"thresholdTokens":200000,"operator":"gt","standard":{"inputRate":4,"cachedInputRate":0.4,"outputRate":18},"batch":{"inputRate":2,"cachedInputRate":0.4,"outputRate":9}},"cacheStorage":{"rate":4.5,"unit":"USD per 1M cached tokens per hour"},"sourceUrls":["https://ai.google.dev/gemini-api/docs/pricing","https://ai.google.dev/gemini-api/docs/models"],"sourceLabel":"Google Gemini API pricing and model documentation"},{"id":"google-gemini-3-flash-preview","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Google","display":"Gemini 3 Flash Preview","modelId":"gemini-3-flash-preview","lifecycleStatus":"preview","note":"Official paid-tier text token rates; hourly context-cache storage is recorded separately.","standard":{"inputRate":0.5,"cachedInputRate":0.05,"outputRate":3},"batch":{"inputRate":0.25,"cachedInputRate":0.05,"outputRate":1.5},"cacheStorage":{"rate":1,"unit":"USD per 1M cached tokens per hour"},"sourceUrls":["https://ai.google.dev/gemini-api/docs/pricing","https://ai.google.dev/gemini-api/docs/models"],"sourceLabel":"Google Gemini API pricing and model documentation"},{"id":"google-gemini-2.5-pro","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Google","display":"Gemini 2.5 Pro","modelId":"gemini-2.5-pro","lifecycleStatus":"ga","shutdownAt":"2026-10-16","note":"Official paid-tier text token rates; hourly context-cache storage is recorded separately. Scheduled API shutdown is 2026-10-16.","standard":{"inputRate":1.25,"cachedInputRate":0.125,"outputRate":10},"batch":{"inputRate":0.625,"cachedInputRate":0.125,"outputRate":5},"longContext":{"thresholdTokens":200000,"operator":"gt","standard":{"inputRate":2.5,"cachedInputRate":0.25,"outputRate":15},"batch":{"inputRate":1.25,"cachedInputRate":0.25,"outputRate":7.5}},"cacheStorage":{"rate":4.5,"unit":"USD per 1M cached tokens per hour"},"sourceUrls":["https://ai.google.dev/gemini-api/docs/pricing","https://ai.google.dev/gemini-api/docs/models","https://ai.google.dev/gemini-api/docs/deprecations"],"sourceLabel":"Google Gemini API pricing and model documentation"},{"id":"google-gemini-2.5-flash","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Google","display":"Gemini 2.5 Flash","modelId":"gemini-2.5-flash","lifecycleStatus":"ga","contextWindowTokens":1000000,"shutdownAt":"2026-10-16","note":"Official paid-tier text token rates; hourly context-cache storage is recorded separately. Scheduled API shutdown is 2026-10-16.","standard":{"inputRate":0.3,"cachedInputRate":0.03,"outputRate":2.5},"batch":{"inputRate":0.15,"cachedInputRate":0.03,"outputRate":1.25},"cacheStorage":{"rate":1,"unit":"USD per 1M cached tokens per hour"},"sourceUrls":["https://ai.google.dev/gemini-api/docs/pricing","https://ai.google.dev/gemini-api/docs/models","https://ai.google.dev/gemini-api/docs/deprecations"],"sourceLabel":"Google Gemini API pricing and model documentation"},{"id":"google-gemini-2.5-flash-lite","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Google","display":"Gemini 2.5 Flash-Lite","modelId":"gemini-2.5-flash-lite","lifecycleStatus":"ga","shutdownAt":"2026-10-16","note":"Official paid-tier text token rates; hourly context-cache storage is recorded separately. Scheduled API shutdown is 2026-10-16.","standard":{"inputRate":0.1,"cachedInputRate":0.01,"outputRate":0.4},"batch":{"inputRate":0.05,"cachedInputRate":0.01,"outputRate":0.2},"cacheStorage":{"rate":1,"unit":"USD per 1M cached tokens per hour"},"sourceUrls":["https://ai.google.dev/gemini-api/docs/pricing","https://ai.google.dev/gemini-api/docs/models","https://ai.google.dev/gemini-api/docs/deprecations"],"sourceLabel":"Google Gemini API pricing and model documentation"},{"id":"xai-grok-4.5","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"xAI","display":"Grok 4.5","modelId":"grok-4.5","lifecycleStatus":"ga","note":"Official text token rates; long-context pricing applies to the whole request at the threshold.","standard":{"inputRate":2,"cachedInputRate":0.3,"outputRate":6},"batch":{"inputRate":2,"cachedInputRate":0.3,"outputRate":6},"longContext":{"thresholdTokens":200000,"operator":"gte","standard":{"inputRate":4,"cachedInputRate":0.6,"outputRate":12}},"sourceUrls":["https://docs.x.ai/developers/pricing","https://docs.x.ai/developers/models"],"sourceLabel":"xAI API pricing and model documentation"},{"id":"xai-grok-build-0.1","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"xAI","display":"Grok Build 0.1","modelId":"grok-build-0.1","lifecycleStatus":"preview","note":"Official text token rates; long-context pricing applies to the whole request at the threshold.","standard":{"inputRate":1,"cachedInputRate":0.2,"outputRate":2},"batch":{"inputRate":1,"cachedInputRate":0.2,"outputRate":2},"longContext":{"thresholdTokens":200000,"operator":"gte","standard":{"inputRate":2,"cachedInputRate":0.4,"outputRate":4}},"sourceUrls":["https://docs.x.ai/developers/pricing","https://docs.x.ai/developers/models"],"sourceLabel":"xAI API pricing and model documentation"},{"id":"xai-grok-4.3","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"xAI","display":"Grok 4.3","modelId":"grok-4.3","lifecycleStatus":"ga","note":"Official text token rates; long-context pricing applies to the whole request at the threshold.","standard":{"inputRate":1.25,"cachedInputRate":0.2,"outputRate":2.5},"batch":{"inputRate":1,"cachedInputRate":0.16,"outputRate":2},"longContext":{"thresholdTokens":200000,"operator":"gte","standard":{"inputRate":2.5,"cachedInputRate":0.4,"outputRate":5},"batch":{"inputRate":2,"cachedInputRate":0.32,"outputRate":4}},"sourceUrls":["https://docs.x.ai/developers/pricing","https://docs.x.ai/developers/models"],"sourceLabel":"xAI API pricing and model documentation"},{"id":"xai-grok-4.20-0309-reasoning","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"xAI","display":"Grok 4.20 Reasoning","modelId":"grok-4.20-0309-reasoning","lifecycleStatus":"ga","note":"Official text token rates; long-context pricing applies to the whole request at the threshold.","standard":{"inputRate":1.25,"cachedInputRate":0.2,"outputRate":2.5},"batch":{"inputRate":1,"cachedInputRate":0.16,"outputRate":2},"longContext":{"thresholdTokens":200000,"operator":"gte","standard":{"inputRate":2.5,"cachedInputRate":0.4,"outputRate":5},"batch":{"inputRate":2,"cachedInputRate":0.32,"outputRate":4}},"sourceUrls":["https://docs.x.ai/developers/pricing","https://docs.x.ai/developers/models"],"sourceLabel":"xAI API pricing and model documentation"},{"id":"xai-grok-4.20-0309-non-reasoning","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"xAI","display":"Grok 4.20 Non-Reasoning","modelId":"grok-4.20-0309-non-reasoning","lifecycleStatus":"ga","note":"Official text token rates; long-context pricing applies to the whole request at the threshold.","standard":{"inputRate":1.25,"cachedInputRate":0.2,"outputRate":2.5},"batch":{"inputRate":1,"cachedInputRate":0.16,"outputRate":2},"longContext":{"thresholdTokens":200000,"operator":"gte","standard":{"inputRate":2.5,"cachedInputRate":0.4,"outputRate":5},"batch":{"inputRate":2,"cachedInputRate":0.32,"outputRate":4}},"sourceUrls":["https://docs.x.ai/developers/pricing","https://docs.x.ai/developers/models"],"sourceLabel":"xAI API pricing and model documentation"},{"id":"xai-grok-4.20-multi-agent-0309","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"xAI","display":"Grok 4.20 Multi-Agent","modelId":"grok-4.20-multi-agent-0309","lifecycleStatus":"preview","note":"Official text token rates; long-context pricing applies to the whole request at the threshold.","standard":{"inputRate":1.25,"cachedInputRate":0.2,"outputRate":2.5},"batch":{"inputRate":1,"cachedInputRate":0.16,"outputRate":2},"longContext":{"thresholdTokens":200000,"operator":"gte","standard":{"inputRate":2.5,"cachedInputRate":0.4,"outputRate":5},"batch":{"inputRate":2,"cachedInputRate":0.32,"outputRate":4}},"sourceUrls":["https://docs.x.ai/developers/pricing","https://docs.x.ai/developers/models"],"sourceLabel":"xAI API pricing and model documentation"},{"id":"deepseek-deepseek-v4-flash","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"DeepSeek","display":"DeepSeek V4 Flash","modelId":"deepseek-v4-flash","lifecycleStatus":"preview","contextWindowTokens":1000000,"pricingNotice":"Peak-hour pricing at 2x has been announced without an effective date and is not active.","note":"Official cache-hit, cache-miss, and output rates; cache writes and storage are not independently priced.","standard":{"inputRate":0.14,"cachedInputRate":0.0028,"outputRate":0.28},"sourceUrls":["https://api-docs.deepseek.com/quick_start/pricing/","https://api-docs.deepseek.com/news/news260424/","https://api-docs.deepseek.com/guides/kv_cache/"],"sourceLabel":"DeepSeek API pricing, release, and cache documentation"},{"id":"deepseek-deepseek-v4-pro","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"DeepSeek","display":"DeepSeek V4 Pro","modelId":"deepseek-v4-pro","lifecycleStatus":"preview","contextWindowTokens":1000000,"pricingNotice":"Peak-hour pricing at 2x has been announced without an effective date and is not active.","note":"Official cache-hit, cache-miss, and output rates; cache writes and storage are not independently priced.","standard":{"inputRate":0.435,"cachedInputRate":0.003625,"outputRate":0.87},"sourceUrls":["https://api-docs.deepseek.com/quick_start/pricing/","https://api-docs.deepseek.com/news/news260424/","https://api-docs.deepseek.com/guides/kv_cache/"],"sourceLabel":"DeepSeek API pricing, release, and cache documentation"},{"id":"mistral-mistral-medium-3-5","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Mistral","display":"Mistral Medium 3.5","modelId":"mistral-medium-3-5","lifecycleStatus":"ga","contextWindowTokens":256000,"note":"Official text token rates; no combined batch-cache price is inferred from separate controls.","standard":{"inputRate":1.5,"cachedInputRate":0.15,"outputRate":7.5},"batch":{"inputRate":0.75,"outputRate":3.75},"sourceUrls":["https://mistral.ai/pricing/api/","https://docs.mistral.ai/models/overview"],"sourceLabel":"Mistral API pricing and model documentation"},{"id":"mistral-mistral-small-2603","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Mistral","display":"Mistral Small 4","modelId":"mistral-small-2603","lifecycleStatus":"ga","contextWindowTokens":256000,"note":"Official text token rates; no combined batch-cache price is inferred from separate controls.","standard":{"inputRate":0.15,"cachedInputRate":0.015,"outputRate":0.6},"batch":{"inputRate":0.075,"outputRate":0.3},"sourceUrls":["https://mistral.ai/pricing/api/","https://docs.mistral.ai/models/overview"],"sourceLabel":"Mistral API pricing and model documentation"},{"id":"mistral-mistral-large-2512","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Mistral","display":"Mistral Large 3","modelId":"mistral-large-2512","lifecycleStatus":"ga","contextWindowTokens":256000,"note":"Official text token rates; no combined batch-cache price is inferred from separate controls.","standard":{"inputRate":0.5,"cachedInputRate":0.05,"outputRate":1.5},"batch":{"inputRate":0.25,"outputRate":0.75},"sourceUrls":["https://mistral.ai/pricing/api/","https://docs.mistral.ai/models/overview"],"sourceLabel":"Mistral API pricing and model documentation"},{"id":"mistral-ministral-3b-2512","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Mistral","display":"Ministral 3 3B","modelId":"ministral-3b-2512","lifecycleStatus":"ga","contextWindowTokens":256000,"note":"Official text token rates; no combined batch-cache price is inferred from separate controls.","standard":{"inputRate":0.1,"cachedInputRate":0.01,"outputRate":0.1},"batch":{"inputRate":0.05,"outputRate":0.05},"sourceUrls":["https://mistral.ai/pricing/api/","https://docs.mistral.ai/models/overview"],"sourceLabel":"Mistral API pricing and model documentation"},{"id":"mistral-ministral-8b-2512","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Mistral","display":"Ministral 3 8B","modelId":"ministral-8b-2512","lifecycleStatus":"ga","contextWindowTokens":256000,"note":"Official text token rates; no combined batch-cache price is inferred from separate controls.","standard":{"inputRate":0.15,"cachedInputRate":0.015,"outputRate":0.15},"batch":{"inputRate":0.075,"outputRate":0.075},"sourceUrls":["https://mistral.ai/pricing/api/","https://docs.mistral.ai/models/overview"],"sourceLabel":"Mistral API pricing and model documentation"},{"id":"mistral-ministral-14b-2512","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Mistral","display":"Ministral 3 14B","modelId":"ministral-14b-2512","lifecycleStatus":"ga","contextWindowTokens":256000,"note":"Official text token rates; no combined batch-cache price is inferred from separate controls.","standard":{"inputRate":0.2,"cachedInputRate":0.02,"outputRate":0.2},"batch":{"inputRate":0.1,"outputRate":0.1},"sourceUrls":["https://mistral.ai/pricing/api/","https://docs.mistral.ai/models/overview"],"sourceLabel":"Mistral API pricing and model documentation"},{"id":"mistral-codestral-2508","unit":"USD per 1M tokens","verifiedAt":"2026-08-03","provider":"Mistral","display":"Codestral","modelId":"codestral-2508","lifecycleStatus":"ga","contextWindowTokens":128000,"note":"Official text token rates; no combined batch-cache price is inferred from separate controls.","standard":{"inputRate":0.3,"cachedInputRate":0.03,"outputRate":0.9},"batch":{"inputRate":0.15,"outputRate":0.45},"sourceUrls":["https://mistral.ai/pricing/api/","https://docs.mistral.ai/models/overview"],"sourceLabel":"Mistral API pricing and model documentation"}]}