tokenpricingCanonical AI model pricing

Pricing math for 3,000+ models — CLI, SDKs, webhook notifications, and a live dashboard, backed by an in-repo database synced every six hours.

💸

Cache-aware pricing

Input, output, and cache read/write rates per million tokens, normalized across OpenRouter and LiteLLM.

🧮

One-line pricing lookups and workload cost math from Python, TypeScript, or your shell — with multi-currency conversion.

🔔

Subscribe to pricing changes and model lifecycle events with HMAC-signed deliveries and retry-safe dispatch.

🗃️

Versioned JSON snapshots in the repository — current prices, full history, and a changelog you can diff and audit.