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.
More from Models
- MissionReport benchmark: only 3 of 540 AI-generated government reports pass all criteria — Exp_Mark · 2026-10-27
- Local beats cloud: Qwen 3.8 FN handles private student data as well as frontier models — dr_lm · 2026-10-27
- Aidan Gomez: model's CoT said no tool calls right before making them — aidangomez · 2026-10-27
- Nat Lambert: Cohere's model is narrow RL training on internal infra ill-suited for open weights — natolambert · 2026-10-27
- OpenAI teases DOTS is coming to Europe 'soon' — mark_k · 2026-10-27
- Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27