Anthropic answer cut off mid-sentence: stop_reason max_tokens, and thinking budget eats the same budget

Truncated answers: read stop_reason, then the budgets

Symptom

Responses end mid-thought. The message stop_reason is max_tokens instead of end_turn.

Confirm the cause

stop_reason: max_tokens means the turn hit the output ceiling. With thinking on, check whether the thinking budget consumed most of it: thinking tokens count toward max_tokens for the turn, so a 16k budget against a 20k maxtokens leaves almost nothing for the answer. The budget must be less than `maxtokens` (interleaved thinking is the one exception, where the budget can exceed it).

Fix

1. Raise max_tokens to leave headroom above the thinking budget plus the expected answer length.
2. Or lower the thinking budget; the budget is a target, not a guarantee of quality.
3. Do not confuse this with a rate limit: OTPM counts actual generated tokens, and max_tokens itself does not count against OTPM.

Verify

The next response on the same prompt returns stop_reason: end_turn with a complete answer. If it still truncates, the budget is still too large relative to max_tokens.

stopreason values, the budgettokens must be less than maxtokens rule, and thinking counting toward maxtokens are documented on the streaming and extended thinking pages. Verified live at https://docs.anthropic.com/en/api/messages-streaming and https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking.