🧮

Free AI & Cloud Cost Calculators

Work out what an AI feature will actually cost before you build it. Estimate API spend for OpenAI, Claude and Gemini from your token usage, compare providers side by side, count tokens precisely with a real tokenizer, calculate cloud GPU costs, estimate response latency, and model the ROI of an AI project.

Everything runs in your browser using bundled pricing data, so there's nothing to sign up for and no usage tracking.

What's included

  • Per-provider cost calculators for OpenAI, Claude and Gemini.
  • A side-by-side LLM API pricing comparison to find the cheapest fit.
  • A token counter using a real GPT tokenizer, with cost estimates.
  • Cloud GPU cost calculator for H100, A100, L4 and similar.
  • LLM latency estimator and an AI project ROI calculator.

How LLM pricing works

Providers charge per token — roughly ¾ of a word in English — and bill input (your prompt) separately from output (the model's reply), with output usually costing more. Costs scale with both request volume and prompt length, which is why a long system prompt sent on every request can dominate a bill. These calculators let you plug in realistic numbers before committing to a model.

Frequently asked questions

How accurate are these estimates?

They use bundled reference pricing that can lag official changes, so treat them as planning estimates and confirm current rates on the provider's own pricing page before committing budget.

What is a token?

A token is a chunk of text — about four characters, or three-quarters of an English word. Models read and write in tokens, and providers bill per token.

Which model is cheapest?

It depends on your input/output mix. Lighter models cost far less per token and handle simpler tasks well; the comparison calculator applies your actual usage to each provider.

Do I need an account?

No. The calculators run entirely in your browser with no signup and no data collection.