jargon

Applied AI·Tokens

the request fit fine and the answer still stopped mid-sentence, because the output cap is a separate and much smaller limit.

Context length vs max output

Draft summary, pending review

Two different limits. The context window bounds everything combined; a separate, usually much smaller, limit bounds how many tokens one response may generate. Hitting either produces different failure modes: an error on input, truncation on output.

Commonly confused with