Glossary
Token
The small chunk of text, roughly a few characters or part of a word, that models read and generate, and the unit most AI usage is billed in.
Models don't see words the way we do; they break text into tokens, where a token is often a short piece of a word. A rough rule of thumb is that one token is about four characters of English.
Tokens matter for two practical reasons: they are the unit you usually pay per, and they are how the context window is measured. Longer prompts and answers mean more tokens, which means higher cost and more space used.
How we use it
We keep an eye on token usage when designing prompts and retrieval, trimming waste so your AI features stay fast and cost-effective at volume.
Related terms
Get in touch
Want to put this into practice?
If this concept is relevant to something you're building, a short note is the fastest way to get practical help.