{"schema_version":1,"currency":"USD","unit":"per 1M tokens","last_verified_at":"2026-07-04","changelog":[{"date":"2026-07-04","provider":"DeepSeek","summary":"Verified DeepSeek V4 Flash and V4 Pro pricing from the official DeepSeek API pricing page.","source_url":"https://api-docs.deepseek.com/quick_start/pricing"},{"date":"2026-07-04","provider":"OpenAI","summary":"Verified GPT-5.5 and GPT-5.4 family standard API pricing from the official OpenAI pricing page.","source_url":"https://platform.openai.com/docs/pricing"},{"date":"2026-07-04","provider":"Anthropic","summary":"Verified current Claude first-party API pricing from the official Anthropic pricing page.","source_url":"https://docs.anthropic.com/en/docs/about-claude/pricing"},{"date":"2026-07-04","provider":"Google","summary":"Verified Gemini 3 Flash and Gemini 2.5 family standard text pricing from the official Gemini API pricing page.","source_url":"https://ai.google.dev/gemini-api/docs/pricing"},{"date":"2026-07-04","provider":"Groq","summary":"Verified Groq on-demand LLM token pricing from the official Groq pricing page.","source_url":"https://groq.com/pricing/"},{"date":"2026-07-04","provider":"Together AI","summary":"Verified selected Together AI serverless inference prices from the official Together AI pricing page.","source_url":"https://www.together.ai/pricing"},{"date":"2026-07-04","provider":"xAI","summary":"Verified Grok Build 0.1 token pricing from the official xAI docs overview.","source_url":"https://docs.x.ai/overview"},{"date":"2026-07-04","provider":"TLDL","summary":"Kept Mistral, Fireworks token inference, and OpenRouter aggregate pricing as source-pending where the official source is not a stable per-model token table in this dataset yet.","source_url":"https://www.tldl.io/api/pricing.json"}],"models":[{"provider":"DeepSeek","model_id":"deepseek-v4-flash","display_name":"DeepSeek V4 Flash","input_per_mtok":0.14,"cached_input_per_mtok":0.0028,"output_per_mtok":0.28,"context_window":1000000,"max_output_tokens":384000,"source_url":"https://api-docs.deepseek.com/quick_start/pricing","verified_at":"2026-07-04","status":"verified","notes":"DeepSeek says deepseek-chat and deepseek-reasoner map to V4 Flash compatibility modes until deprecation on 2026-07-24."},{"provider":"DeepSeek","model_id":"deepseek-v4-pro","display_name":"DeepSeek V4 Pro","input_per_mtok":0.435,"cached_input_per_mtok":0.003625,"output_per_mtok":0.87,"context_window":1000000,"max_output_tokens":384000,"source_url":"https://api-docs.deepseek.com/quick_start/pricing","verified_at":"2026-07-04","status":"verified","notes":"Official DeepSeek pricing table, fetched 2026-07-04."},{"provider":"OpenAI","model_id":"gpt-5.5","display_name":"GPT-5.5","input_per_mtok":5,"cached_input_per_mtok":0.5,"output_per_mtok":30,"context_window":null,"max_output_tokens":null,"source_url":"https://platform.openai.com/docs/pricing","verified_at":"2026-07-04","status":"verified","notes":"Official OpenAI standard short-context pricing. Long-context pricing is higher and is listed separately on the official pricing page."},{"provider":"OpenAI","model_id":"gpt-5.4","display_name":"GPT-5.4","input_per_mtok":2.5,"cached_input_per_mtok":0.25,"output_per_mtok":15,"context_window":null,"max_output_tokens":null,"source_url":"https://platform.openai.com/docs/pricing","verified_at":"2026-07-04","status":"verified","notes":"Official OpenAI standard short-context pricing. Long-context pricing is higher and is listed separately on the official pricing page."},{"provider":"OpenAI","model_id":"gpt-5.4-mini","display_name":"GPT-5.4 mini","input_per_mtok":0.75,"cached_input_per_mtok":0.075,"output_per_mtok":4.5,"context_window":null,"max_output_tokens":null,"source_url":"https://platform.openai.com/docs/pricing","verified_at":"2026-07-04","status":"verified","notes":"Official OpenAI standard pricing."},{"provider":"OpenAI","model_id":"gpt-5.4-nano","display_name":"GPT-5.4 nano","input_per_mtok":0.2,"cached_input_per_mtok":0.02,"output_per_mtok":1.25,"context_window":null,"max_output_tokens":null,"source_url":"https://platform.openai.com/docs/pricing","verified_at":"2026-07-04","status":"verified","notes":"Official OpenAI standard pricing."},{"provider":"Anthropic","model_id":"claude-opus-4.8","display_name":"Claude Opus 4.8","input_per_mtok":5,"cached_input_per_mtok":0.5,"output_per_mtok":25,"context_window":null,"max_output_tokens":null,"source_url":"https://docs.anthropic.com/en/docs/about-claude/pricing","verified_at":"2026-07-04","status":"verified","notes":"Official Anthropic first-party Claude API base input, cache hit, and output pricing."},{"provider":"Anthropic","model_id":"claude-sonnet-5-intro","display_name":"Claude Sonnet 5","input_per_mtok":2,"cached_input_per_mtok":0.2,"output_per_mtok":10,"context_window":null,"max_output_tokens":null,"source_url":"https://docs.anthropic.com/en/docs/about-claude/pricing","verified_at":"2026-07-04","status":"verified","notes":"Official introductory Claude Sonnet 5 pricing through 2026-08-31; Anthropic lists standard pricing starting 2026-09-01."},{"provider":"Anthropic","model_id":"claude-sonnet-4.6","display_name":"Claude Sonnet 4.6","input_per_mtok":3,"cached_input_per_mtok":0.3,"output_per_mtok":15,"context_window":null,"max_output_tokens":null,"source_url":"https://docs.anthropic.com/en/docs/about-claude/pricing","verified_at":"2026-07-04","status":"verified","notes":"Official Anthropic first-party Claude API base input, cache hit, and output pricing."},{"provider":"Anthropic","model_id":"claude-haiku-4.5","display_name":"Claude Haiku 4.5","input_per_mtok":1,"cached_input_per_mtok":0.1,"output_per_mtok":5,"context_window":null,"max_output_tokens":null,"source_url":"https://docs.anthropic.com/en/docs/about-claude/pricing","verified_at":"2026-07-04","status":"verified","notes":"Official Anthropic first-party Claude API base input, cache hit, and output pricing."},{"provider":"Google","model_id":"gemini-3-flash-preview","display_name":"Gemini 3 Flash Preview","input_per_mtok":0.5,"cached_input_per_mtok":0.05,"output_per_mtok":3,"context_window":null,"max_output_tokens":null,"source_url":"https://ai.google.dev/gemini-api/docs/pricing","verified_at":"2026-07-04","status":"verified","notes":"Official Gemini API paid-tier standard text/image/video input and output pricing. Audio input pricing differs."},{"provider":"Google","model_id":"gemini-2.5-pro","display_name":"Gemini 2.5 Pro","input_per_mtok":1.25,"cached_input_per_mtok":0.125,"output_per_mtok":10,"context_window":1000000,"max_output_tokens":null,"source_url":"https://ai.google.dev/gemini-api/docs/pricing","verified_at":"2026-07-04","status":"verified","notes":"Official Gemini API paid-tier standard pricing for prompts up to 200k tokens. Google lists higher prices for prompts over 200k tokens."},{"provider":"Google","model_id":"gemini-2.5-flash","display_name":"Gemini 2.5 Flash","input_per_mtok":0.3,"cached_input_per_mtok":0.03,"output_per_mtok":2.5,"context_window":1000000,"max_output_tokens":null,"source_url":"https://ai.google.dev/gemini-api/docs/pricing","verified_at":"2026-07-04","status":"verified","notes":"Official Gemini API paid-tier standard text/image/video input and output pricing. Audio input pricing differs."},{"provider":"Google","model_id":"gemini-2.5-flash-lite","display_name":"Gemini 2.5 Flash-Lite","input_per_mtok":0.1,"cached_input_per_mtok":0.01,"output_per_mtok":0.4,"context_window":null,"max_output_tokens":null,"source_url":"https://ai.google.dev/gemini-api/docs/pricing","verified_at":"2026-07-04","status":"verified","notes":"Official Gemini API paid-tier standard text/image/video input and output pricing. Audio input pricing differs."},{"provider":"xAI","model_id":"grok-build-0.1","display_name":"Grok Build 0.1","input_per_mtok":1,"cached_input_per_mtok":null,"output_per_mtok":2,"context_window":256000,"max_output_tokens":null,"source_url":"https://docs.x.ai/overview","verified_at":"2026-07-04","status":"verified","notes":"Official xAI overview pricing for the Grok Build coding model. The same page did not expose token prices for Grok 4.3 in the fetched content."},{"provider":"Mistral","model_id":"source-pending","display_name":"Mistral models","input_per_mtok":null,"cached_input_per_mtok":null,"output_per_mtok":null,"context_window":null,"max_output_tokens":null,"source_url":"https://docs.mistral.ai/getting-started/models/models_overview/","verified_at":null,"status":"source_pending","notes":"Official model docs are tracked, but a stable per-model token pricing table was not found in the fetched docs. Do not publish Mistral prices until verified from an official pricing table."},{"provider":"Together AI","model_id":"together-deepseek-v4-pro","display_name":"DeepSeek V4 Pro on Together","input_per_mtok":1.74,"cached_input_per_mtok":0.2,"output_per_mtok":3.48,"context_window":null,"max_output_tokens":null,"source_url":"https://www.together.ai/pricing","verified_at":"2026-07-04","status":"verified","notes":"Official Together AI serverless inference pricing."},{"provider":"Together AI","model_id":"together-minimax-m3","display_name":"MiniMax M3 on Together","input_per_mtok":0.3,"cached_input_per_mtok":0.06,"output_per_mtok":1.2,"context_window":null,"max_output_tokens":null,"source_url":"https://www.together.ai/pricing","verified_at":"2026-07-04","status":"verified","notes":"Official Together AI serverless inference pricing."},{"provider":"Together AI","model_id":"together-gpt-oss-120b","display_name":"gpt-oss-120B on Together","input_per_mtok":0.15,"cached_input_per_mtok":null,"output_per_mtok":0.6,"context_window":null,"max_output_tokens":null,"source_url":"https://www.together.ai/pricing","verified_at":"2026-07-04","status":"verified","notes":"Official Together AI serverless inference pricing."},{"provider":"Together AI","model_id":"together-lfm2-24b-a2b","display_name":"LFM2 24B A2B on Together","input_per_mtok":0.03,"cached_input_per_mtok":null,"output_per_mtok":0.12,"context_window":null,"max_output_tokens":null,"source_url":"https://www.together.ai/pricing","verified_at":"2026-07-04","status":"verified","notes":"Official Together AI serverless inference pricing."},{"provider":"Fireworks","model_id":"source-pending","display_name":"Fireworks models","input_per_mtok":null,"cached_input_per_mtok":null,"output_per_mtok":null,"context_window":null,"max_output_tokens":null,"source_url":"https://fireworks.ai/pricing","verified_at":null,"status":"source_pending","notes":"Official pricing page exposes serverless, fine-tuning, and GPU-hour pricing, but the fetched content points per-token estimates to a separate blog. Keep token pricing pending until a stable official per-model token table is available."},{"provider":"Groq","model_id":"groq-gpt-oss-20b","display_name":"GPT OSS 20B on Groq","input_per_mtok":0.075,"cached_input_per_mtok":0.0375,"output_per_mtok":0.3,"context_window":128000,"max_output_tokens":null,"source_url":"https://groq.com/pricing/","verified_at":"2026-07-04","status":"verified","notes":"Official Groq on-demand LLM pricing. Groq lists cache-hit pricing for this model in its prompt caching section."},{"provider":"Groq","model_id":"groq-gpt-oss-120b","display_name":"GPT OSS 120B on Groq","input_per_mtok":0.15,"cached_input_per_mtok":0.075,"output_per_mtok":0.6,"context_window":128000,"max_output_tokens":null,"source_url":"https://groq.com/pricing/","verified_at":"2026-07-04","status":"verified","notes":"Official Groq on-demand LLM pricing. Groq lists cache-hit pricing for this model in its prompt caching section."},{"provider":"Groq","model_id":"groq-llama-4-scout","display_name":"Llama 4 Scout on Groq","input_per_mtok":0.11,"cached_input_per_mtok":null,"output_per_mtok":0.34,"context_window":128000,"max_output_tokens":null,"source_url":"https://groq.com/pricing/","verified_at":"2026-07-04","status":"verified","notes":"Official Groq on-demand LLM pricing."},{"provider":"Groq","model_id":"groq-llama-3.1-8b-instant","display_name":"Llama 3.1 8B Instant on Groq","input_per_mtok":0.05,"cached_input_per_mtok":null,"output_per_mtok":0.08,"context_window":128000,"max_output_tokens":null,"source_url":"https://groq.com/pricing/","verified_at":"2026-07-04","status":"verified","notes":"Official Groq on-demand LLM pricing."},{"provider":"OpenRouter","model_id":"source-pending","display_name":"OpenRouter models","input_per_mtok":null,"cached_input_per_mtok":null,"output_per_mtok":null,"context_window":null,"max_output_tokens":null,"source_url":"https://openrouter.ai/api/v1/models","verified_at":null,"status":"source_pending","notes":"Provider exposes model pricing through its models API; ingestion needs a deterministic model-selection policy before publishing aggregate OpenRouter prices."}]}