{"updated":"11 August 2026","unit":"USD per 1,000,000 tokens","note":"Verify against each vendor's pricing page before budgeting.","count":30,"models":[{"vendor":"Anthropic","model":"Claude Opus 4.1","input_per_mtok":15.0,"output_per_mtok":75.0,"cached_input_per_mtok":1.5,"batch_50pct":true,"context_k":200,"source":"https://www.anthropic.com/pricing"},{"vendor":"Anthropic","model":"Claude Sonnet 4.5","input_per_mtok":3.0,"output_per_mtok":15.0,"cached_input_per_mtok":0.3,"batch_50pct":true,"context_k":200,"source":"https://www.anthropic.com/pricing"},{"vendor":"Anthropic","model":"Claude Haiku 4.5","input_per_mtok":1.0,"output_per_mtok":5.0,"cached_input_per_mtok":0.1,"batch_50pct":true,"context_k":200,"source":"https://www.anthropic.com/pricing"},{"vendor":"Anthropic","model":"Claude Haiku 3.5","input_per_mtok":0.8,"output_per_mtok":4.0,"cached_input_per_mtok":0.08,"batch_50pct":true,"context_k":200,"source":"https://www.anthropic.com/pricing"},{"vendor":"OpenAI","model":"GPT-5","input_per_mtok":1.25,"output_per_mtok":10.0,"cached_input_per_mtok":0.125,"batch_50pct":true,"context_k":400,"source":"https://openai.com/api/pricing/"},{"vendor":"OpenAI","model":"GPT-5 mini","input_per_mtok":0.25,"output_per_mtok":2.0,"cached_input_per_mtok":0.025,"batch_50pct":true,"context_k":400,"source":"https://openai.com/api/pricing/"},{"vendor":"OpenAI","model":"GPT-5 nano","input_per_mtok":0.05,"output_per_mtok":0.4,"cached_input_per_mtok":0.005,"batch_50pct":true,"context_k":400,"source":"https://openai.com/api/pricing/"},{"vendor":"OpenAI","model":"o3","input_per_mtok":2.0,"output_per_mtok":8.0,"cached_input_per_mtok":0.5,"batch_50pct":true,"context_k":200,"source":"https://openai.com/api/pricing/"},{"vendor":"OpenAI","model":"GPT-4.1","input_per_mtok":2.0,"output_per_mtok":8.0,"cached_input_per_mtok":0.5,"batch_50pct":true,"context_k":1000,"source":"https://openai.com/api/pricing/"},{"vendor":"OpenAI","model":"GPT-4.1 mini","input_per_mtok":0.4,"output_per_mtok":1.6,"cached_input_per_mtok":0.1,"batch_50pct":true,"context_k":1000,"source":"https://openai.com/api/pricing/"},{"vendor":"OpenAI","model":"GPT-4.1 nano","input_per_mtok":0.1,"output_per_mtok":0.4,"cached_input_per_mtok":0.025,"batch_50pct":true,"context_k":1000,"source":"https://openai.com/api/pricing/"},{"vendor":"OpenAI","model":"GPT-4o","input_per_mtok":2.5,"output_per_mtok":10.0,"cached_input_per_mtok":1.25,"batch_50pct":true,"context_k":128,"source":"https://openai.com/api/pricing/"},{"vendor":"OpenAI","model":"GPT-4o mini","input_per_mtok":0.15,"output_per_mtok":0.6,"cached_input_per_mtok":0.075,"batch_50pct":true,"context_k":128,"source":"https://openai.com/api/pricing/"},{"vendor":"Google","model":"Gemini 2.5 Pro (<200k)","input_per_mtok":1.25,"output_per_mtok":10.0,"cached_input_per_mtok":0.31,"batch_50pct":true,"context_k":1000,"source":"https://ai.google.dev/gemini-api/docs/pricing"},{"vendor":"Google","model":"Gemini 2.5 Flash","input_per_mtok":0.3,"output_per_mtok":2.5,"cached_input_per_mtok":0.075,"batch_50pct":true,"context_k":1000,"source":"https://ai.google.dev/gemini-api/docs/pricing"},{"vendor":"Google","model":"Gemini 2.5 Flash-Lite","input_per_mtok":0.1,"output_per_mtok":0.4,"cached_input_per_mtok":0.025,"batch_50pct":true,"context_k":1000,"source":"https://ai.google.dev/gemini-api/docs/pricing"},{"vendor":"Google","model":"Gemini 2.0 Flash","input_per_mtok":0.1,"output_per_mtok":0.4,"cached_input_per_mtok":0.025,"batch_50pct":true,"context_k":1000,"source":"https://ai.google.dev/gemini-api/docs/pricing"},{"vendor":"DeepSeek","model":"DeepSeek-V3 (chat)","input_per_mtok":0.27,"output_per_mtok":1.1,"cached_input_per_mtok":0.07,"batch_50pct":false,"context_k":64,"source":"https://api-docs.deepseek.com/quick_start/pricing"},{"vendor":"DeepSeek","model":"DeepSeek-R1 (reasoner)","input_per_mtok":0.55,"output_per_mtok":2.19,"cached_input_per_mtok":0.14,"batch_50pct":false,"context_k":64,"source":"https://api-docs.deepseek.com/quick_start/pricing"},{"vendor":"xAI","model":"Grok 3","input_per_mtok":3.0,"output_per_mtok":15.0,"cached_input_per_mtok":0.75,"batch_50pct":false,"context_k":131,"source":"https://docs.x.ai/docs/models"},{"vendor":"xAI","model":"Grok 3 mini","input_per_mtok":0.3,"output_per_mtok":0.5,"cached_input_per_mtok":0.075,"batch_50pct":false,"context_k":131,"source":"https://docs.x.ai/docs/models"},{"vendor":"Mistral","model":"Mistral Large","input_per_mtok":2.0,"output_per_mtok":6.0,"cached_input_per_mtok":2.0,"batch_50pct":true,"context_k":128,"source":"https://mistral.ai/pricing"},{"vendor":"Mistral","model":"Mistral Small","input_per_mtok":0.1,"output_per_mtok":0.3,"cached_input_per_mtok":0.1,"batch_50pct":true,"context_k":128,"source":"https://mistral.ai/pricing"},{"vendor":"Meta (Together)","model":"Llama 3.3 70B Turbo","input_per_mtok":0.88,"output_per_mtok":0.88,"cached_input_per_mtok":0.88,"batch_50pct":false,"context_k":128,"source":"https://www.together.ai/pricing"},{"vendor":"Meta (Together)","model":"Llama 3.1 8B Turbo","input_per_mtok":0.18,"output_per_mtok":0.18,"cached_input_per_mtok":0.18,"batch_50pct":false,"context_k":128,"source":"https://www.together.ai/pricing"},{"vendor":"Amazon","model":"Nova Pro","input_per_mtok":0.8,"output_per_mtok":3.2,"cached_input_per_mtok":0.2,"batch_50pct":true,"context_k":300,"source":"https://aws.amazon.com/bedrock/pricing/"},{"vendor":"Amazon","model":"Nova Lite","input_per_mtok":0.06,"output_per_mtok":0.24,"cached_input_per_mtok":0.015,"batch_50pct":true,"context_k":300,"source":"https://aws.amazon.com/bedrock/pricing/"},{"vendor":"Amazon","model":"Nova Micro","input_per_mtok":0.035,"output_per_mtok":0.14,"cached_input_per_mtok":0.00875,"batch_50pct":true,"context_k":128,"source":"https://aws.amazon.com/bedrock/pricing/"},{"vendor":"Cohere","model":"Command R+","input_per_mtok":2.5,"output_per_mtok":10.0,"cached_input_per_mtok":2.5,"batch_50pct":false,"context_k":128,"source":"https://cohere.com/pricing"},{"vendor":"Cohere","model":"Command R","input_per_mtok":0.15,"output_per_mtok":0.6,"cached_input_per_mtok":0.15,"batch_50pct":false,"context_k":128,"source":"https://cohere.com/pricing"}]}