New "xhigh" Effort Level / Claude Code v2.1.111

What

A new effort level called "xhigh" is added between "high" and "max", providing deeper reasoning capability exclusive to Opus 4.7.

Usage

# Set effort via CLI flag
claude --effort xhigh

# Set effort in-session
/effort xhigh

Details

The effort scale now has five levels: low, medium, high, xhigh, max
"xhigh" is described as "Deeper reasoning than high, just below maximum (Opus 4.7 only)"
"xhigh" is the automatic default effort level when using Opus 4.7
If "xhigh" is requested on a model that doesn't support it, it falls back to "high"
The effortLevel setting now accepts: low, medium, high, xhigh, max
The /effort command help text is updated accordingly

Evidence

"xhigh" effort level (search for "xhigh") — 0 occurrences in v2.1.110, 40 in v2.1.111. Default logic in bF1() at line ~237923 (search for "opus-4-7" returning "xhigh")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

How sure we are

One source agreesOne thing we can check says the same as this entry.

Anthropic's release notes agreeClaude Opus 4.7 xhigh is now available! Use /effort to tune speed vs. intelligence

See this entry in the whole of v2.1.111 →

The build it came inv2.1.111

16 Apr 2026 · 23 entries, this one is #2.

Either side of it

v2.1.110Older
v2.1.112Newer

Open the release →

Names in this entry

settinglow
A new modelSettings config key stores an effort level per model, from low to xhigh.
settingmedium
Workflow size now defaults to medium, and an admin policy setting overrides whatever you chose.
settinghigh
The bundled Claude API skill docs now target the new Opus, covering thinking defaults, fallbacks and fast mode.
settingxhigh
The bundled Claude API skill docs now target the new Opus, covering thinking defaults, fallbacks and fast mode.
settingmax
The bundled Claude API skill docs now target the new Opus, covering thinking defaults, fallbacks and fast mode.
settingeffortLevel
Set a default effort level for models without a saved level of their own
slash/effort
Set the effort level: low to xhigh, max, ultracode, or auto; status prints it. max and ultracode are session-only; the ultracode key persists. Run it while Claude is responding and, once you confirm the cache warning, if Claude Code shows one, Claude Code applies the new level to the next request in that turn. Before v2.1.242, Claude Code decided from a feature flag it fetched from Anthropic whether to run the command mid-turn or queue it until the turn finished, and always queued it in a session that doesn't fetch feature flags, such as on a third-party provider. Works in -p

Anthropic's notes

Upstream's own release notes for v2.1.111 name something this entry names, so the two are probably about the same change. Probably: the pairing is made on a shared name rather than on the words around it.

Claude Opus 4.7 xhigh is now available! Use /effort to tune speed vs. intelligence
Added xhigh effort level for Opus 4.7, sitting between high and max. Available via /effort, --effort, and the model picker; other models fall back to high
/effort now opens an interactive slider when called without arguments, with arrow-key navigation between levels and Enter to confirm

Is this right?

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.