Follow Discord
Sweep 30 Oct 2026 · 01:02Z Build v2.1.314 532 read Stable v2.1.308 Latest v2.1.314 Next v2.1.314 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Code CLI 27 Oct 2026
One change · claude-code

Model configuration changedmodel-config

Nearest release: v2.1.311, published 8 hours before upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Upstream edited this page at 27 Oct 2026 04:06 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 27 Oct 2026 04:07 UTC.

Upstream edited
Recorded here
Lines+8added
Lines−2removed
From line 538 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits84to this page, all time

The whole hunk

from line 538, old and new numbered
/
lines
from line 538
538538A different level applies in cases such as these:
539539 
540540* **Your own change**: once you choose an effort level, pick a model in `/model`, or resume the session later, the flagged request's level no longer carries over.
541* **Skill effort**: a level that a skill's `effort` frontmatter set for the flagged request applies to that turn, and later turns run at the level the [effort resolution order](#adjust-effort-level) gives the fallback model.
541* **Effort set for one turn**: if you raised the flagged turn with `ultrathink`, or a skill's `effort` frontmatter set its level, that level applies to that turn. Later turns run at the level the [effort resolution order](#adjust-effort-level) gives the fallback model.
542542 
543543In the session, run `/effort status` to see the level in effect, or `/effort` to change it.
544544 
from line 670
670670 
671671#### Use ultrathink for one-off deep reasoning
672672 
673Include `ultrathink` anywhere in your prompt to request deeper reasoning on that turn without changing your session effort setting. Claude Code recognizes the keyword and adds an in-context instruction. The effort level sent to the API is unchanged. Claude Code passes other phrases such as "think", "think hard", and "think more" through as ordinary prompt text and doesn't recognize them as keywords.
673Include `ultrathink` anywhere in your prompt to request deeper reasoning on that turn without changing your session effort setting. Claude Code recognizes the keyword and adds an in-context instruction. Claude Code passes other phrases such as "think", "think hard", and "think more" through as ordinary prompt text and doesn't recognize them as keywords.
674 
675Typed in the terminal prompt, the word can also raise that turn to `xhigh` effort. When it can, the word shows in rainbow colors. Requires Claude Code v2.1.311 or later. If the word isn't rainbow when you start a new turn, try one of these:
676 
677* Retype it outside anything such as quotes, brackets, a path, or a command, in a prompt that doesn't start with `/`
678* Unset `CLAUDE_CODE_EFFORT_LEVEL` if it's set below `xhigh`, raise your own [`maxEffortLevel`](https://code.claude.com/docs/en/settings-reference#maxeffortlevel) to `xhigh` or above, or ask an organization admin to raise your [organization's limit](#organization-effort-limits)
679* Run `/model` in your session to switch to an Opus 5.5, Sonnet 5.5, Haiku 5.5, or Fable 5.1 model. Where the word can't raise a turn, such as on Amazon Bedrock, [set the effort level](#set-the-effort-level) instead
674680 
675681#### Set the effort level
676682 
Feedback