LLM API Cost Calculator

Headline prices hide the real bill. Enter your actual usage and see what each model truly costs you per month.

Requests per day

Input tokens per request

Output tokens per request

Cache hit rate: 85%

Estimated monthly bill

Model	Input $/1M	Output $/1M	Monthly

How to read this

The bar chart shows each model's monthly cost relative to the cheapest option. Output tokens are priced 4–8× higher than input on most models, so your output length and cache hit rate move the bill far more than switching between adjacent models. Measure your real input and output averages from the usage block every API response returns — don't guess.