Anthropic’s Opus 5 can now error out when thinking is off but max effort is on

AlexKim · x · 2026-07-28

A follow-up note repeats the key Opus 5 warning: if thinking is disabled while xhigh/max effort is set, the API returns a 400.

It also reinforces that maxtokens now limits thinking and output together, so tight budgets can cut the answer off mid-way.

Related event: Claude Opus 5 arrives with near-Fable coding and new self-checking behavior(11 posts)→

Original post →

More from Models

Models channel →