{"dataset":"LLM API Pricing Tracker","source":"https://techfastforward.com/data/llm-pricing","license":"Free to use with attribution and a link back to the source page","last_updated":"2026-08-06","unit":"USD per 1M tokens","models":[{"provider":"Anthropic","model":"claude-fable-5","input_per_mtok":10,"output_per_mtok":50,"context_window":"1M","notes":null,"source_url":"https://docs.claude.com/en/docs/about-claude/pricing","effective_date":"2026-06-11"},{"provider":"Anthropic","model":"claude-opus-4-7","input_per_mtok":5,"output_per_mtok":25,"context_window":"1M","notes":null,"source_url":"https://docs.claude.com/en/docs/about-claude/pricing","effective_date":"2026-06-11"},{"provider":"Anthropic","model":"claude-opus-4-8","input_per_mtok":5,"output_per_mtok":25,"context_window":"1M","notes":null,"source_url":"https://docs.claude.com/en/docs/about-claude/pricing","effective_date":"2026-06-11"},{"provider":"Anthropic","model":"claude-opus-5","input_per_mtok":5,"output_per_mtok":25,"context_window":"1M","notes":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","effective_date":"2026-08-05"},{"provider":"Anthropic","model":"claude-sonnet-4-6","input_per_mtok":3,"output_per_mtok":15,"context_window":"1M","notes":null,"source_url":"https://docs.claude.com/en/docs/about-claude/pricing","effective_date":"2026-06-11"},{"provider":"Anthropic","model":"claude-sonnet-5","input_per_mtok":2,"output_per_mtok":10,"context_window":"1M","notes":"Introductory pricing through August 31, 2026; standard pricing $3/$15 thereafter","source_url":"https://platform.claude.com/docs/en/about-claude/pricing","effective_date":"2026-08-05"},{"provider":"Anthropic","model":"claude-haiku-4-5","input_per_mtok":1,"output_per_mtok":5,"context_window":"200K","notes":null,"source_url":"https://docs.claude.com/en/docs/about-claude/pricing","effective_date":"2026-06-11"},{"provider":"DeepSeek","model":"deepseek-v4-pro","input_per_mtok":0.435,"output_per_mtok":0.87,"context_window":"1M","notes":"Cache-miss input rate; cache-hit input is $0.003625","source_url":"https://api-docs.deepseek.com/quick_start/pricing","effective_date":"2026-06-11"},{"provider":"DeepSeek","model":"deepseek-v4-flash","input_per_mtok":0.14,"output_per_mtok":0.28,"context_window":"1M","notes":"Cache-miss input rate; cache-hit input is $0.0028","source_url":"https://api-docs.deepseek.com/quick_start/pricing","effective_date":"2026-06-11"},{"provider":"Google","model":"gemini-3.1-pro-preview","input_per_mtok":2,"output_per_mtok":12,"context_window":null,"notes":"Rate for prompts up to 200K tokens; above 200K is $4 in / $18 out","source_url":"https://ai.google.dev/gemini-api/docs/pricing","effective_date":"2026-06-11"},{"provider":"Google","model":"gemini-3.6-flash","input_per_mtok":1.5,"output_per_mtok":7.5,"context_window":null,"notes":"Text/image/video input rate","source_url":"https://ai.google.dev/gemini-api/docs/pricing","effective_date":"2026-08-05"},{"provider":"Google","model":"gemini-3.5-flash","input_per_mtok":1.5,"output_per_mtok":9,"context_window":null,"notes":null,"source_url":"https://ai.google.dev/gemini-api/docs/pricing","effective_date":"2026-06-11"},{"provider":"Google","model":"gemini-2.5-pro","input_per_mtok":1.25,"output_per_mtok":10,"context_window":null,"notes":"Rate for prompts up to 200K tokens; above 200K is $2.50 in / $15.00 out","source_url":"https://ai.google.dev/gemini-api/docs/pricing","effective_date":"2026-06-12"},{"provider":"Google","model":"gemini-3-flash-preview","input_per_mtok":0.5,"output_per_mtok":3,"context_window":null,"notes":"Text/image/video input rate; audio input is $1.00","source_url":"https://ai.google.dev/gemini-api/docs/pricing","effective_date":"2026-06-11"},{"provider":"Google","model":"gemini-2.5-flash","input_per_mtok":0.3,"output_per_mtok":2.5,"context_window":null,"notes":"Text/image/video input rate; batch/flex tier is 50% off","source_url":"https://ai.google.dev/gemini-api/docs/pricing","effective_date":"2026-06-12"},{"provider":"Google","model":"gemini-3.5-flash-lite","input_per_mtok":0.3,"output_per_mtok":2.5,"context_window":null,"notes":"Hybrid reasoning model","source_url":"https://ai.google.dev/gemini-api/docs/pricing","effective_date":"2026-08-06"},{"provider":"Google","model":"gemini-3.1-flash-lite","input_per_mtok":0.25,"output_per_mtok":1.5,"context_window":null,"notes":"Text/image/video input rate; audio input is $0.50","source_url":"https://ai.google.dev/gemini-api/docs/pricing","effective_date":"2026-06-11"},{"provider":"Google","model":"gemini-2.5-flash-lite","input_per_mtok":0.1,"output_per_mtok":0.4,"context_window":null,"notes":"Most cost-efficient option","source_url":"https://ai.google.dev/gemini-api/docs/pricing","effective_date":"2026-06-12"},{"provider":"OpenAI","model":"o1-pro","input_per_mtok":150,"output_per_mtok":600,"context_window":"short","notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-08-06"},{"provider":"OpenAI","model":"gpt-5.4-pro","input_per_mtok":30,"output_per_mtok":180,"context_window":null,"notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-06-11"},{"provider":"OpenAI","model":"gpt-5.5-pro","input_per_mtok":30,"output_per_mtok":180,"context_window":null,"notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-06-11"},{"provider":"OpenAI","model":"o3-pro","input_per_mtok":20,"output_per_mtok":80,"context_window":"short","notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-08-06"},{"provider":"OpenAI","model":"o1","input_per_mtok":15,"output_per_mtok":60,"context_window":"short","notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-08-06"},{"provider":"OpenAI","model":"gpt-5-pro","input_per_mtok":15,"output_per_mtok":120,"context_window":"short","notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-08-06"},{"provider":"OpenAI","model":"gpt-5.6-sol","input_per_mtok":5,"output_per_mtok":30,"context_window":null,"notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-07-09"},{"provider":"OpenAI","model":"chat-latest","input_per_mtok":5,"output_per_mtok":30,"context_window":null,"notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-07-09"},{"provider":"OpenAI","model":"gpt-5.5","input_per_mtok":5,"output_per_mtok":30,"context_window":null,"notes":"Short-context rate; long-context tier is $10 in / $45 out","source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-06-11"},{"provider":"OpenAI","model":"gpt-5.4","input_per_mtok":2.5,"output_per_mtok":15,"context_window":null,"notes":"Short-context rate; long-context tier is $5 in / $22.50 out","source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-06-11"},{"provider":"OpenAI","model":"gpt-4o","input_per_mtok":2.5,"output_per_mtok":10,"context_window":"short","notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-08-06"},{"provider":"OpenAI","model":"o3","input_per_mtok":2,"output_per_mtok":8,"context_window":"short","notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-08-06"},{"provider":"OpenAI","model":"gpt-5.6-terra","input_per_mtok":2,"output_per_mtok":12,"context_window":null,"notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-08-05"},{"provider":"OpenAI","model":"gpt-5.3-codex","input_per_mtok":1.75,"output_per_mtok":14,"context_window":null,"notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-06-11"},{"provider":"OpenAI","model":"gpt-5","input_per_mtok":1.25,"output_per_mtok":10,"context_window":"short","notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-08-06"},{"provider":"OpenAI","model":"o3-mini","input_per_mtok":1.1,"output_per_mtok":4.4,"context_window":"short","notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-08-06"},{"provider":"OpenAI","model":"gpt-5.4-mini","input_per_mtok":0.75,"output_per_mtok":4.5,"context_window":null,"notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-06-11"},{"provider":"OpenAI","model":"gpt-3.5-turbo","input_per_mtok":0.5,"output_per_mtok":1.5,"context_window":"short","notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-08-06"},{"provider":"OpenAI","model":"gpt-5-mini","input_per_mtok":0.25,"output_per_mtok":2,"context_window":"short","notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-08-06"},{"provider":"OpenAI","model":"gpt-5.6-luna","input_per_mtok":0.2,"output_per_mtok":1.2,"context_window":null,"notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-08-05"},{"provider":"OpenAI","model":"gpt-5.4-nano","input_per_mtok":0.2,"output_per_mtok":1.25,"context_window":null,"notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-06-11"},{"provider":"OpenAI","model":"gpt-4o-mini","input_per_mtok":0.15,"output_per_mtok":0.6,"context_window":"short","notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-08-06"},{"provider":"OpenAI","model":"gpt-5-nano","input_per_mtok":0.05,"output_per_mtok":0.4,"context_window":"short","notes":null,"source_url":"https://developers.openai.com/api/docs/pricing","effective_date":"2026-08-06"},{"provider":"xAI","model":"grok-4.5","input_per_mtok":2,"output_per_mtok":6,"context_window":"1M","notes":"Most capable xAI option for general tasks","source_url":"https://docs.x.ai/docs/models","effective_date":"2026-07-08"},{"provider":"xAI","model":"grok-4.20-0309-non-reasoning","input_per_mtok":1.25,"output_per_mtok":2.5,"context_window":"1M","notes":null,"source_url":"https://docs.x.ai/docs/models","effective_date":"2026-06-12"},{"provider":"xAI","model":"grok-4.20-0309-reasoning","input_per_mtok":1.25,"output_per_mtok":2.5,"context_window":"1M","notes":null,"source_url":"https://docs.x.ai/docs/models","effective_date":"2026-06-11"},{"provider":"xAI","model":"grok-4.20-multi-agent-0309","input_per_mtok":1.25,"output_per_mtok":2.5,"context_window":"1M","notes":null,"source_url":"https://docs.x.ai/docs/models","effective_date":"2026-06-12"},{"provider":"xAI","model":"grok-4.3","input_per_mtok":1.25,"output_per_mtok":2.5,"context_window":"1M","notes":null,"source_url":"https://docs.x.ai/docs/models","effective_date":"2026-06-11"},{"provider":"xAI","model":"grok-build-0.1","input_per_mtok":1,"output_per_mtok":2,"context_window":"256K","notes":null,"source_url":"https://docs.x.ai/docs/models","effective_date":"2026-06-11"}]}