LLM API cost calculator
Pick a scenario or enter your own traffic. Monthly cost is calculated for every model at once (30 days), cheapest first.
| Model | Monthly cost | Per 1K requests |
|---|
How the estimate works
Each request costs input tokens × input price, with the cache-hit share billed at the cached-input price, plus output tokens × output price. Batch mode uses the provider's batch prices where published.
FAQ
Does cached input cost less?
Yes. Providers bill input tokens read from the prompt cache at a fraction of the normal input price, often 10%. Anthropic also charges extra to write the cache, which this calculator does not include.
What does the batch toggle do?
Batch APIs process requests asynchronously, typically within 24 hours, at about half price. Models without a batch price are shown at their normal price.
Why is my real bill different?
Reasoning models bill hidden thinking tokens as output, long prompts can trigger higher long-context rates, and tool calls add tokens. Treat results as an estimate.