Prompt Token Cost Calculator

Project text-token spend from a real prompt — with cache hits, batch pricing, and a cross-model comparison.

AI and LLM visibility Last reviewed Nov 11, 2026 Free, no signup

Model

Prices are standard-tier list $/1M input · output tokens (as of Nov 11, 2026).

System prompt (optional)

User / main prompt

Completion sample (optional)

Or expected output tokens

Used when completion text is empty. Best if you already know vendor token counts.

Cache hit %

% of input billed at cached rate.

Calls / day

Days

Use Batch API pricing (async, typically ~50% of list)

Paste prompt text and choose a model to estimate tokens and USD cost.

Estimate

Per call

Input tokens

Output tokens

Period cost

Context used

Batch pricing on

Model	Provider	$/1M in·out	Per call	Period

FAQ

Yes. Fair-use rate limits keep the suite available for everyone.

Yes. CDNs, registry redaction, and heuristics mean you should verify critical findings in your own environment.

Runs are processed to return results. Avoid pasting secrets or personal data you would not put in a public tool.