Token
The unit an LLM reads and writes in. A token is roughly three-quarters of a word, so "learning" might be one or two tokens.
Usage is billed and limited in tokens, and the context window is measured in them. Tokens are the currency of AI.
Frequently asked questions
How many tokens are in a page of text?
A token is roughly three-quarters of a word, so a typical single-spaced page of a few hundred words lands somewhere in the several-hundred-token range. Short common words are often one token, while a longer word can be split into two or more.
Why should I care about tokens?
Because tokens are the currency of AI: usage is billed in them, and the amount of text a model can handle at once is measured in them. More tokens in your request and its reply generally means more cost and more of the context window used up.
Is a token the same as a word or a letter?
Not exactly. A token is a chunk of text that is often about three-quarters of a word, so it can be a whole short word or just part of a longer one. The model reads and writes in these chunks rather than in whole words or single letters.
New to all this? Start with what an AI agent really is, browse the full glossary, or explore the learning hub.
← Back to the glossary