Model configuration changedmodel-config
Upstream edited this page at 11 Nov 2026 14:14 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 11 Nov 2026 14:37 UTC.
Upstream edited
Recorded here
Lines+9added
Lines−2removed
From line
768
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits93to this page, all time
#### Where you can't turn thinking off
The whole hunk
from line 768, old and new numbered
/
from line 768
768768| :- | :- |
769769| Toggle for the current session | Press `Option+T` on macOS or `Alt+T` on Windows and Linux |
770770| Set the global default | Run `/config` and toggle thinking mode. Saved as `alwaysThinkingEnabled` in `~/.claude/settings.json` |
771| Disable through an environment variable | Set [`MAX_THINKING_TOKENS=0`](https://code.claude.com/docs/en/env-vars), which turns thinking off on the Anthropic API except on Opus 5.5, Sonnet 5.5, Haiku 5.5, and Fable models. On [third-party providers](https://code.claude.com/docs/en/third-party-integrations.md), Claude Code omits the `thinking` parameter instead, and adaptive-reasoning models may still think |
771| Disable through an environment variable | Set [`MAX_THINKING_TOKENS=0`](https://code.claude.com/docs/en/env-vars) |
772772
773Claude Code collapses thinking output by default. Press `Ctrl+O` to toggle verbose mode and see the reasoning as gray italic text. Interactive sessions on the Anthropic API receive redacted thinking blocks by default, so set [`showThinkingSummaries: true`](https://code.claude.com/docs/en/settings-reference#showthinkingsummaries) in settings if you want the full summaries available when you expand. You are charged for all thinking tokens generated, even when collapsed or redacted.
774
775#### Where you can't turn thinking off
776
773777You can't turn thinking off on Opus 5.5, Sonnet 5.5, Haiku 5.5, or the Fable models. The session toggle and the `/config` row show `Thinking can't be turned off` for these models instead of offering the switch, and a saved `alwaysThinkingEnabled: false` or `MAX_THINKING_TOKENS=0` has no effect there. On these models, the model decides per step how much to think based on the effort level. The saved setting applies again when you switch to a model that accepts it.
774778
775Claude Code collapses thinking output by default. Press `Ctrl+O` to toggle verbose mode and see the reasoning as gray italic text. Interactive sessions on the Anthropic API receive redacted thinking blocks by default, so set `showThinkingSummaries: true` in [settings](https://code.claude.com/docs/en/settings.md) if you want the full summaries available when you expand. You are charged for all thinking tokens generated, even when collapsed or redacted.
779To stop or reduce thinking, use the step for your provider:
780
781* **Anthropic API**: you can turn thinking off on models such as `claude-opus-5`, `claude-sonnet-5`, and `claude-haiku-4-5`. [Aliases](#model-aliases) such as `sonnet` select models where you can't, so [set the model](#setting-your-model) by its ID.
782* **[Third-party providers](https://code.claude.com/docs/en/third-party-integrations.md)**: on providers such as Amazon Bedrock and Microsoft Foundry, models with [adaptive reasoning](#adaptive-reasoning-and-fixed-thinking-budgets) may still think with thinking off. [Lower the effort level](#set-the-effort-level) to reduce thinking.
776783
777784### Extended context
778785
No line in this hunk matches that.