← Glossary / 15 of 100

n. / AI agents

Token usage

Definition

Token usage is the number of input (prompt) and output (completion) tokens a language model processes for a call, which determines both its cost and how much of the context window it uses.

In more detail

Cached input tokens are usually billed at a lower rate, so good tracking records input, cached and output tokens separately.

Definitions are the start.

Open a real trace and watch these terms move.