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
Context window
The amount of text a model can consider at once, measured in tokens, covering both your input and its output.
Model routing
Sending each task, or each part of a task, to the model best suited for it, rather than using one model for everything.
Reasoning model
A model built to work through problems step by step before answering, rather than responding in a single pass.
Try multi-model on your task
One prompt, several models, one answer. Free to start, no card.
Get started