The unit AI providers bill for.
A token is a chunk of text produced by a tokenizer. A token can be a whole word, part of a word, punctuation, or whitespace. English text averages roughly four characters per token, but code, JSON, and non-Latin scripts tokenize differently.
Every input and output token is priced. Estimating tokens from character counts is convenient but can be off by 20–40% for code or multilingual prompts.