SMALL TOOLS FOR SOFTWARE DECISIONS
Make the units explicit.
Developer calculators and practical guides for estimating AI API usage, keeping input and output costs separate, and documenting a reproducible budget.
AI token cost calculator →Make the next decision clearer.
Begin with your own evidence
Estimate inference charges using token counts and prices you enter. The calculator includes no built-in provider pricing, so it cannot silently rely on an outdated rate.
Cost = requests × (input tokens × input price + output tokens × output price) ÷ 1,000,000. The illustrative starting values produce $20 input cost and $25 output cost, totaling $45.
Example prices are invented, not provider quotes. Cached tokens, reasoning tokens, tool calls, images, audio, retries, storage, taxes and batch discounts are excluded. Token counts vary by model and content; use measured usage for a better estimate.
How we prepare these resources →