Cost lab · Verified pricing index

AI API cost calculator

Enter your token volume or messages per day, then adjust caching, batch use, and reasoning output. No email or sign-up.

Prices from official provider docs Calculations verified — never paid placements

Your usage

Tokens you send to the model per month
Tokens the model generates per month

Token density changes by language and content. Measure a real prompt with the token counter, or start with one of the workload presets above.

Enter usage above to see cost calculations.

Monthly cost

APIs cheapest-first · self-hosted listed separately
Save models in workspace

Loading…

Records without a complete per-token API rate are listed separately. Missing API pricing is not a zero-cost estimate; licensing, hardware, cloud, storage, networking, and operations remain outside this calculator. See methodology for sources.

Also useful

→ Token counter — count a real prompt before you price it → Model rankings — capability + price together → Model recommender — guided questions → Price per use case — when cost changes everything → How to cut your token bill

Frequently asked questions

What's the cheapest AI API?

In the current benchr snapshot, DeepSeek V4-Flash has the lowest listed hosted rate at $0.14 input and $0.28 output per million tokens. Records without a complete API price are listed separately; a missing API rate does not make licensing, hardware, cloud, or operations free.

How much does Claude cost per month?

Depends on which tier. Enter your actual input, output, caching, and reasoning-token assumptions above for a model-by-model figure.

Does this include cached pricing?

Yes. Set the repeated-input percentage and the calculator applies each model's documented cached-input rate when available. Batch and cache discounts are not stacked.

Is the pricing up to date?

Prices come from the shared benchr model index, verified against official provider pricing pages and recorded in the changelog. Provider prices can change without notice.

Updates

Follow new pieces through RSS, recent releases, and the changelog.