LLM API Cost Calculator
Estimate and compare LLM API costs across models from token usage.
Comparison
Totals shown for 10,000 calls.
Recommended next steps
Related tools
Estimate text tokens and rough AI API costs before running a prompt.
Convert between tokens and an approximate word or character count.
Estimate the cost of generating images across model presets.
Frequently asked questions
Cost per call is (input tokens ÷ 1,000,000 × input price) + (output tokens ÷ 1,000,000 × output price), since most providers price tokens per million. The total is that per-call cost multiplied by your number of calls. Edit the per-model input and output prices to match your provider's current published rates.
No — the prices shown are editable example values, not live rates, and they are not tied to any specific provider. Always replace them with the current numbers from your provider's official pricing page before relying on the estimate. Prices change often.
No. The calculator runs entirely in your browser. The token counts, call volumes, and prices you enter stay on this page and are never sent to a server.
Input tokens are roughly your prompt plus any context you send; output tokens are what the model generates back. A common rough estimate is about four characters per token in English. Use a tokenizer or our token estimator for a closer count, then enter the per-call figures here.
Last updated 2026-06-23.