Tools

Free calculators for 32 models. Everything runs in your browser.

Price a request on any of 32 models, including cache and long-context rates.

Rank every model by cost for the same request, side by side.

Rates per million tokens for 32 models, checked 2026-10-10.

Find how many reuses it takes for prompt caching to save money.

Compare full history, a sliding window and summarization over many turns.

See how your prompts and reserved output fill a model's context window.

An illustrative model of how input, output and cached tokens drive quality.

Drop your Claude Code logs to see turns, cache hits and cost. Nothing is uploaded.