LLM API cost calculator
Work out what a prompt costs on each model before you build. Paste the prompt, set the expected answer length and how many requests you expect, and compare models from cheapest to most expensive.
How to use the LLM cost calculator
- Paste a real prompt, including the system prompt and any context you add.
- Set Answer length to the size of reply you expect.
- Set Requests to your expected daily or monthly volume.
- Sort by cost and compare; edit prices to match your contract.
What you get
- Input and output cost per request
- Total for any number of requests
- Cheapest model highlighted
- Editable prices, kept in your browser
About the LLM cost calculator
Output costs more
Most models charge several times more for the tokens they write than for the tokens they read. A long answer can cost more than a long prompt, so set the answer length carefully.
What is not included
Batch, cached-input and volume discounts, image and audio inputs, and tool calls are not included. They usually lower or raise the cost from the list price shown.
Frequently asked questions
- How current are the prices?
- They load live from a public price list and update every few hours; the last update time is shown under the table. Follow the link beside each model to check the provider's page.
- Can I add my own price?
- Yes. Press Edit prices and type your own input and output prices per million tokens.
- Is my prompt uploaded?
- No. Everything runs in your browser.