AI token and cost calculator
Estimate how many tokens a piece of text uses, whether it fits a model's context window and what an API call would cost at the prices you enter.
How to read the results
Models do not read words. They read tokens: short chunks of characters. In English a token averages about four characters, so 1,000 tokens is roughly 750 words. Other languages, code and unusual names use more tokens for the same length.
The context window is the most a model can consider at once, counting your prompt, any files and its own reply. If your text uses most of the window, there is little room left for the answer. Our guide to tokens and context windows explains the idea in full.
The prices in the cost calculator are placeholders. Replace them with the current figures from the provider you use; they change often and differ between models.