token

A token is the basic unit of text that a large language model works with. Rather than reading whole words or letters, models break text into tokens, chunks that are, on average, about three-quarters of a word. Common words may be a single token, while longer or unusual words are split into several.

Tokens matter for two practical reasons. First, a model’s context window, how much it can consider at once, is measured in tokens, not words. Second, most AI services charge by the token, so the length of your input and the model’s output directly affects the cost.

Understanding tokens demystifies a lot of AI pricing and limits: when a provider quotes “a million tokens” or bills per token, they are really talking about roughly this many chunks of text going in and out.