Follow Discord
Sweep 22 Sep 2026 · 17:19Z Build v2.1.280 501 read Stable v2.1.267 Latest v2.1.280 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
Claude Code v2.1.260 ·

Adaptive thinking has an opt-out for specific models, unresolved by default

Adaptive thinking is now default; an env var can revert to the old mode for certain models.

TierUse it nowhow much it should matter to you
Useful3my rating, 1 to 5
Signal2worth watching, 1 to 5
AreaThinking Modewhat it touches
KindImprovementsin v2.1.260,
Use it now Notable

Adaptive thinking is now default; an env var can revert to the old mode for certain models.

Adaptive thinking mode is now the shipped default for per-turn thinking behavior. Setting CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING forces the older enabled mode instead, but only when the canonical model name includes opus-4-6 or sonnet-4-6; otherwise adaptive mode applies as normal.

Read from
Names in the bundleCLAUDE_CODE_DISABLE_ADAPTIVE_THINKING
What the documentation says
Documented inclaude-code/desktop
Since it was published

The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.

Confirmed since Anthropic's documentation has since written up CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING, on Connect Claude Code to an LLM gateway. | `400` errors naming `thinking` or `adaptive`, such as `Input tag 'adaptive' found` | The upstream model build doesn't accept adaptive reasoning, which Claude Code requests for Claude 4.6 and later models | Upgrade the gateway's upstream.… llm-gateway-connect see the edit
How sure we are
One source agreesOne thing we can check says the same as this entry.
Anthropic's documentation agreesAnthropic's documentation has since written up CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING, on Connect Claude Code to an LLM gateway.

See this entry in the whole of v2.1.260 →

Feedback