How it works
Cost = requests × (input tokens × input rate + output tokens × output rate) ÷ 1,000,000.
Worked example
10,000 requests with 1,000 input tokens at 1/million and 500 output tokens at 4/million cost 30.
Assumptions and limits
Rates are editable examples, not provider prices. Excludes caching, separately billed reasoning, tools, images, audio, and retries.
See it in real data
Mobile apps
Estimated revenue and downloads from the App Store and Google Play
Frequently asked questions
How do I use the ai token cost calculator?
Estimate text inference cost using average tokens per request, volume, and input and output prices per million tokens.
Does the currency selection change the rate automatically?
No. Enter rates and costs in the selected currency, converting beforehand if needed.
Do I need an account and are my inputs uploaded?
No account is required. Calculations run in your browser. Entered numbers and text are not included in tool analytics events; only the tool ID, language, and action are recorded.