Token
A token is the basic unit a language model reads and generates, often a word, part of a word, or a punctuation mark.
Before processing a text, a model splits it into tokens. In English, a word corresponds on average to about 1.3 tokens, slightly more in languages with accents or compound words.
The number of tokens determines the cost and speed of a request, and limits how much context a model can process at once, see context window.