Skip to main content

Glossary / Tokens

Glossary

Tokens

In short

The chunks of text models read and write, roughly a few characters each, and the unit most model pricing is based on.

Models do not read characters or whole words; they read tokens, which are pieces of text averaging a few characters. A short word might be one token, a long one several.

Tokens matter for two practical reasons: they are what context windows are measured in, and they are what most model usage is billed on, so longer prompts and answers cost more.

In LLMWeave

Text model cost in LLMWeave is based on tokens, and a weave tracks it per model so you can see the price of each part of a run. Video generation is priced per second of output instead.

Related terms

Try multi-model on your task

One prompt, several models, one answer. Free to start, no card.

Get started