Free tool · No sign-up
LLM Cost Calculator
See what your AI feature will cost at scale, and how much caching saves.
About this tool
How are LLM API costs calculated?
Providers charge per million input and output tokens. Monthly cost is requests multiplied by tokens and the rate, with output usually costing more.
Are these prices current?
The tiers are round example figures, not a provider price sheet, and prices change often. Check your provider before budgeting.
How does caching change the bill?
Repeated prompt prefixes can be billed at a large discount. This calculator assumes cached input costs 10 percent of the normal rate.
Want a real number instead of an estimate?
Bring these results to a free 30-minute call and an engineer will check them against your actual project.