AI Token Cost Calculator
Work out what an AI feature will actually cost before you build it. Pick a model, set your prompt and reply sizes, and see the cost per request, per day and per month — then compare every major model on the same workload.
Asynchronous processing — 50% off at OpenAI, Anthropic and Google
Same workload, every model
Monthly cost for the exact workload set above, cheapest first. Click any row to load that model into the calculator.
Last verified: 16 Oct 2026 — prices checked against the providers’ official pricing pages. INTRO rates and the GPT-4o shutdown are flagged on their rows below.
| Model | Per request | Monthly |
|---|
How the billing works: you pay one rate for tokens you send (input) and a higher rate for tokens the model writes (output, which includes reasoning/thinking tokens). Repeated prompt prefixes read from cache are billed at the much lower cached rate. Prices are standard short-context list prices in USD, checked 16 Oct 2026 — see sources below.