Model configuration changedmodel-config
Nearest release: v2.1.284, published under an hour 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 28 Sep 2026 17:21 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 28 Sep 2026 17:37 UTC.
Upstream edited
Recorded here
Lines+10added
Lines−8removed
From line
611
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits44to this page, all time
The whole hunk
from line 611, old and new numbered
/
from line 611
611611
612612Each level trades token spend against capability. The default suits most coding tasks; adjust when you want a different balance.
613613
614| Level | When to use it |
615| :---------- | :------------------------------------------------------------------------------------------------------------------------------------- |
616| `low` | Reserve for short, scoped, latency-sensitive tasks that are not intelligence-sensitive |
617| `medium` | Reduces token usage for cost-sensitive work that can trade off some intelligence. The default on Opus 5.5 |
618| `high` | Balances token usage and intelligence. The default on every model except Opus 5.5 and Opus 4.7 |
619| `xhigh` | Deeper reasoning at higher token spend. The default on Opus 4.7 |
620| `max` | Can improve performance on demanding tasks but may show diminishing returns and is prone to overthinking. Test before adopting broadly |
621| `ultracode` | A Claude Code setting that plans a [dynamic workflow](/docs/en/workflows) for each substantive task with `xhigh` per-message reasoning |
614| Level | When to use it |
615| :---------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
616| `low` | Quick exchanges where you review each result, such as brainstorming, a first sketch, or a small change like a rename |
617| `medium` | The default on Opus 5.5, where it fits day-to-day engineering work with a clear scope, such as implementing a new feature. On other models, reduces token usage for cost-sensitive work that can trade off some intelligence |
618| `high` | Work where verification matters or edge cases are likely, such as fixing a bug in an existing codebase. The default on every model except Opus 5.5 and Opus 4.7 |
619| `xhigh` | Deeper reasoning at higher token spend. The default on Opus 4.7 |
620| `max` | Hard problems you want Claude to work through without you, such as finding security vulnerabilities. `max` may show diminishing returns and is prone to overthinking, so test before adopting it broadly |
621| `ultracode` | A Claude Code setting that plans a [dynamic workflow](/docs/en/workflows) for each substantive task with `xhigh` per-message reasoning |
622
623In tests on Opus 5.5 and Fable 5.1, Claude at a higher level tested more edge cases and verified more of its work before answering. It also made more choices on its own. At a lower level, Claude returned a starting point sooner, which fits work where you review each result and steer the next step. To see the same tasks run at each level, read [Using Claude Code: Spending your effort](https://claude.dev/blog/spending-your-effort/) on the blog.
622624
623625The effort scale is calibrated per model, so the same level name does not represent the same underlying value across models.
624626
No line in this hunk matches that.