n. / Models and tokens
Definition
Output tokens are the tokens a model generates in its reply. They cost more per token than input tokens and are produced one at a time, so they dominate how long a response takes.
In more detail
Latency grows with the number of output tokens, which is why asking for shorter answers or structured output often speeds up an agent. Models that reason before answering can also spend many output tokens on reasoning you never see, so check the usage numbers rather than the visible text.
Example
A classifier that returns one word uses about 3 output tokens. A model asked to explain its answer may use 300.
Related terms
