whattAI Calculator Suite

Compare live API costs, estimate prompt caching discounts, and analyze GPU self hosting break even points to optimize your AI infrastructure spend.

Choose a Preset

Quickly estimate standard developer or customer workloads.

Adjust parameters to model your custom monthly API volumes.

Requests / Month:5,000

Avg. Input Tokens / Request:1,000

Avg. Output Tokens / Request:500

Model Name	Provider	Cost / 1M Tokens	Monthly Output Vol.	Est. Monthly Cost	Relative Cost