LLM API Cost Calculator
Enter your typical request size and daily volume — see what each major model would cost per request and per month, side by side.
| Model | Input $/M | Output $/M | Per request | Per month |
|---|
Prices verified 2026-07-19 from official provider pricing pages. Standard tier, no caching/batch discounts.
How is this calculated?
Cost per request = (input tokens × input price + output tokens × output price) ÷ 1,000,000. Monthly cost assumes 30 days at your daily request volume.
What's not included?
Prompt-caching discounts (up to 90% on repeated context), batch API discounts (typically 50%), long-context surcharges, and free tiers. Real bills are often lower with caching — treat these numbers as a worst-case baseline.