← Glossary / 45 of 100
n. / Models and tokens
Max tokens
Definition
Max tokens is a setting that caps how many tokens a model may generate in one reply. If the reply hits the cap, it stops mid-sentence and the call reports a length stop reason.
In more detail
It protects you from runaway cost and long waits, but a cap set too low truncates answers and can break structured output, leaving invalid JSON. Watch for runs that end because of length, since they are a common hidden cause of bad outputs and failed parsing.
Example
A summarizer is capped at 200 tokens. A long article produces a reply cut off mid-sentence, and the trace shows the stop reason "length".
