Docs search: xhigh / page 2 of 2 / Source Intelligence

prompting-claude-haiku-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-haiku-5-5 …wledge work, longer agent tasks, and strict instruction following. * `xhigh` and `max` are for work where a quality gain on your evals justifies the cost. Thinking and replies get much longer at these…

prompting-claude-opus-4-8 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-4-8 …ding off capability for faster speed and lower costs. Start with the `xhigh` effort level for coding and agentic use cases, and use a minimum of `high` effort for most intelligence-sensitive use cases…

prompting-claude-opus-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5 …token cost and response time wherever quality holds, and step up to `xhigh` for demanding coding and agentic work. If you carried effort defaults over from a prior model, re-run an effort sweep on yo…

prompting-claude-opus-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5-5 …s 5.5 tends to think more per turn than Claude Opus 5, especially at `xhigh` and `max`. If you keep the `effort` value you set for Claude Opus 5, expect longer turns and more output tokens. Three adju…

prompting-claude-sonnet-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5 …onnet 4.6. For the hardest coding and agentic tasks, raise effort to `xhigh`. Experiment with other effort levels to further tune token usage and intelligence: * **`max`:** Absolute maximum capabilit…

prompting-claude-sonnet-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5 …ude.com/docs/en/build-with-claude/streaming) the response. * Reserve `xhigh` and `max` for work where you've measured a quality gain, because thinking and replies get much longer there. At those level…

task-budgets Claude Developer Platform · in the page build-with-claude/task-budgets …cross the full agentic loop (potentially spanning many requests). At `xhigh` or `max` effort, set `max_tokens` to at least 64k to give Claude room to think and act on each request. * **[Effort](https:…

thinking Claude Developer Platform · in the page build-with-claude/thinking …rks at `low`, `medium`, and `high` effort and returns a 400 error at `xhigh` or `max`. On Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Fable 5.1, Claude Mythos 5.1, Clau…

thinking-steering-and-cost Claude Developer Platform · in the page build-with-claude/thinking-steering-and-cost …nd at the greatest depth, with no constraint on thinking length. | | `xhigh` | Claude thinks more readily and at greater depth than at `high`, suited…

thinking-troubleshooting Claude Developer Platform · in the page build-with-claude/thinking-troubleshooting …/build-with-claude/effort) `high` or below; combining it with effort `xhigh` or `max` returns a 400 error. On Claude Opus 5, this restriction is enforced on each request. On Claude Haiku 5.5, a per-me…

apple-foundation-models Claude Developer Platform · in the page cli-sdks-libraries/libraries/apple-foundation-models …ad, pass a custom reasoning level naming the Claude effort (`.custom("xhigh")` or `.custom("max")`), which maps directly. When no effort is sent, the API uses the model's default level, which differs…

agent-setup Claude Developer Platform · in the page managed-agents/agent-setup …The `effort` field accepts a level string (`low`, `medium`, `high`, `xhigh`, or `max`) or an object such as `{"type": "high"}`. See [Effort levels](https://platform.claude.com/docs/en/build-with-clau…

Or, for Claude Mythos 5.1, which offers the same capabilities to verified organizations: Claude Developer Platform · in the page models/fable-5-1/migration-guide …ges it. Only the named levels are accepted (`low`, `medium`, `high`, `xhigh`, `max`), and the `mid-conversation-output-config-2026-07-01` beta header is required. See [Per-message effort](https://plat…

migration-guide Claude Developer Platform · in the page models/opus-5-5/migration-guide …arameter that controls it. All five levels (`low`, `medium`, `high`, `xhigh`, `max`) are supported, and the default is `medium`. See [Recommended effort levels for Claude Opus 5.5](https://platform.cl…

whats-new-opus-5-5 Claude Developer Platform · in the page models/opus-5-5/whats-new-opus-5-5 …odel tends to think more per turn than Claude Opus 5, most of all at `xhigh` and `max`. Re-run your effort sweep rather than carrying a setting over, and leave room in `max_tokens` for the thinking. S…

migration-guide Claude Developer Platform · in the page models/sonnet-5-5/migration-guide …beta header. It's accepted at `low`, `medium`, and `high` effort. At `xhigh` or `max`, it returns a 400 error. To run at those levels, use adaptive thinking: omit the `thinking` field or send `thinkin…

whats-new-sonnet-5-5 Claude Developer Platform · in the page models/sonnet-5-5/whats-new-sonnet-5-5 …between_tools` is accepted at `low`, `medium`, and `high` effort. At `xhigh` or `max` effort, a request with `between_tools` returns a 400 error. To run at `xhigh` or `max`, use adaptive thinking: omi…

overview Claude Developer Platform · in the page release-notes/overview …effort `high` or below: `thinking: {"type": "disabled"}` with effort `xhigh` or `max` returns a 400 error, a breaking change from Claude Opus 4.8. See [What's new in Claude Opus 5](https://platform.cl…

Agent SDK reference - Python Claude Code CLI · in the page agent-sdk/python …"medium", # Moderate thinking "high", # Deep reasoning "xhigh", # Extended reasoning; falls back to "high" on models that don't support it "max", # Maximum effort ] ``` ### `CanUs…

Manage multiple agents with agent view Claude Code CLI · in the page agent-view …g.md#adjust-effort-level)**: `/effort` with `low`, `medium`, `high`, `xhigh`, or `max`, for example `/effort high`. To start sessions in [ultracode](/docs/en/workflows.md#let-claude-decide-with-ultrac…

Claude Code changelog Claude Code CLI · in the page changelog …ixed web searches and `agent` hook evaluations taking much longer at `xhigh` and `max` effort **2.1.294** October 8, 2026 * Fixed `prompt` and `agent` hooks written as instructions (such as "Block…

CLI reference Claude Code CLI · in the page cli-reference …rt-level) for the current session. Options: `low`, `medium`, `high`, `xhigh`, `max`, or `ultracode`. Available levels depend on the model. `ultracode` requests `xhigh` effort with [ultracode](/docs/en…

Environment variables Claude Code CLI · in the page env-vars …effort level for supported models. Values: `low`, `medium`, `high`, `xhigh`, `max`, or `auto` to use the model default. Available levels depend on the model. Takes precedence over `--effort`, `/effor…

Hooks reference Claude Code CLI · in the page hooks …level) in effect when the hook runs: `"low"`, `"medium"`, `"high"`, `"xhigh"`, or `"max"`. If you set a level the active model doesn't support, `level` reports the level Claude Code ran instead; [Adju…

Monitoring Claude Code CLI · in the page monitoring-usage …djust-effort-level) applied to the request: `low`, `medium`, `high`, `xhigh`, or `max`. Absent when Claude Code sends no effort level, for example on a model that doesn't support effort. Requires Clau…

Claude Code settings Claude Code CLI · in the page settings …t-level) across sessions. Accepts `"low"`, `"medium"`, `"high"`, or `"xhigh"`. Written automatically when you run `/effort` with one of those values. `--effort` and [`CLAUDE_CODE_EFFORT_LEVEL`](/docs/…

Example settings files Claude Code CLI · in the page settings-example …net-5", "modelSettings": { "claude-sonnet-5": { "effortLevel": "xhigh" } }, "editorMode": "vim", "theme": "light-daltonized", "statusLine": { "type": "command", "command": "jq -r…

All settings Claude Code CLI · in the page settings-reference …ng new ones | Plugins and skills | User, local, or managed | | [`syntaxHighlightingDisabled`](#syntaxhighlightingdisabled) | Turn off syntax highlighting in diffs and code blocks | Interface and termi…

Extend Claude with skills Claude Code CLI · in the page skills …el-config.md#adjust-effort-level). Options: `low`, `medium`, `high`, `xhigh`, `max`; available levels depend on the model. | | `context` | No | Set to `fork` to run in a forked subagent context. See […

Customize your status line Claude Code CLI · in the page statusline …`effort.level` | Current reasoning effort (`low`, `medium`, `high`, `xhigh`, or `max`). Reflects the live session value, including mid-session `/effort` changes. Absent when the current model does no…

Create custom subagents Claude Code CLI · in the page sub-agents …s#variables) environment variable. Options: `low`, `medium`, `high`, `xhigh`, `max`; available levels depend on the model. See [Choose an effort level](#choose-an-effort-level) | | `isolation` | No |…

Week 16 · April 13–17, 2026 Claude Code CLI · in the page whats-new/2026-w16 # Week 16 · April 13–17, 2026 > Claude Opus 4.7 with the new xhigh effort level, Routines on Claude Code on the web, mobile push notifications that ping your phone when Claude needs you, a /usage bre…

Week 22 · May 25–29, 2026 Claude Code CLI · in the page whats-new/2026-w22 …u-go, and the Anthropic API. It defaults to high effort; use `/effort xhigh` for harder tasks. Requires v2.1.154 or later. <video autoPlay muted loop playsInline src="https://mintcdn.com/claude-code/…

Week 33 · August 10–14, 2026 Claude Code CLI · in the page whats-new/2026-w33 …o re-enable them[`/code-review`](/docs/en/code-review-local) at high, xhigh, and max effort now runs in a background agent like the other levels[`/plugin install plugin@marketplace`](/docs/en/plugins/…

What's new Claude Code CLI · in the page whats-new/index …and Anthropic API accounts, with high effort by default and `/effort xhigh` for the hardest tasks. Also this week: **dynamic workflows** orchestrate dozens to hundreds of subagents from a script Cla…

Orchestrate subagents at scale with dynamic workflows Claude Code CLI · in the page workflows …ith `claude --effort ultracode`, which also sets the effort level to `xhigh`. To turn it on from the `/effort` slider, press `Tab` to flip the **Ultracode** toggle, then `Enter` to apply it. [Adjust…

Configuration reference Claude Documentation · in the page third-party/claude-desktop/configuration …ed value caps the model at low. > > One of: `low`, `medium`, `high`, `xhigh`, `max` *** #### `defaultModelEffort` enumSince 2.110.0 **Default model effort.** Effort level the default model (the fi…

Configuration changelog Claude Documentation · in the page third-party/claude-desktop/configuration-changelog …"<string>" }, "models": { "defaultEffort": "<low|medium|high|xhigh|max>", "alwaysStartWithDefault": "<boolean>", "catalogEnabled": "<boolean>", "catalogUrl": "<string>" }, "wo…

Models and effort levels Claude Documentation · in the page third-party/claude-desktop/models …model in Chat, Cowork, and Code. Set it to `low`, `medium`, `high`, `xhigh`, or `max`. The picker shows `xhigh` as **Extra**. The **Effort** control doesn't offer levels above the cap. In Code sessi…