Token
A token is the unit of text an LLM processes — roughly 4 characters or about three-quarters of a word in English — and API usage and free allowances are usually measured and priced per token.
A token is a chunk of text — a short word, part of a word, or a punctuation mark. Language models read and generate text token by token, so both your prompt (input) and the model’s reply (output) are counted in tokens.
As a rough rule of thumb in English, 1 token ≈ 4 characters ≈ 0.75 words, so 1,000 tokens is about 750 words. Providers price API calls per token (often with different rates for input and output), and free tiers frequently cap usage in tokens per minute (TPM).
Understanding tokens helps you estimate cost and stay within free limits: shorter prompts and responses use fewer tokens.
Last updated