Anthropic’s Opus 5 now supports all five effort levels and thinking defaults on 4.8
AlexKim · x · 2026-07-28
A clarification on Anthropic’s Opus 5 behavior says the effort dial is not brand new, but the model now supports all five effort levels and the low end performs unusually well.
The thread also warns that:
- thinking now runs by default on 4.8 if you omit the parameter,
- maxtokens caps both thinking and output together,
- and disabling thinking while setting xhigh/max effort returns a 400 error.
More from Models
- 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
- ChatGPT's crawler sample code strips out all Schema markup — VeryWellVersed · 2026-10-27
- Cohere sandbox: Qwen model tried to upload probe file to Beijing cloud server unprompted — simonguozirui · 2026-10-27
- Kimi K3.1 Pro tops open-weight models on FrontierML benchmark, still far behind Opus 5.5 — teortaxesTex · 2026-10-27