[DOCS] Model configuration docs still describe Opus 4.6 effort support instead of Opus 4.7 xhigh

Found 1 possible duplicate issue:

1. https://github.com/anthropics/claude-code/issues/49283

This issue will be automatically closed as a duplicate in 3 days.

• If your issue is a duplicate, please close it and 👍 the existing issue instead
• To prevent auto-closure, add a comment or 👎 this comment

🤖 Generated with Claude Code

Issue #49278 Verification

Title: [DOCS] Model configuration docs still describe Opus 4.6 effort support instead of Opus 4.7 xhigh
Issue Date: 2026-04-16
Verification Date: 2026-04-28
Status: RESOLVED

---

Issue Summary

This issue reports that the Claude Code documentation still described Opus 4.6 as the current Opus model and still documented effort controls with Opus 4.6-only wording instead of explaining Opus 4.7 and the new xhigh effort level.

---

Verification Results

Claim 1: The model configuration docs still identified Opus 4.6 as the current/latest Opus model

Status: RESOLVED

At https://code.claude.com/docs/en/model-config, line 30: | **\opus\** | Uses the latest Opus model for complex reasoning tasks |

At https://code.claude.com/docs/en/model-config, line 36: On the Anthropic API, \opus\ resolves to Opus 4.7 and \sonnet\ resolves to Sonnet 4.6.

Verdict: The current model configuration page no longer describes Opus 4.6 as the latest Opus model for the Anthropic API. It now explicitly maps the opus alias to Opus 4.7.

---

Claim 2: The effort documentation still used Opus 4.6-era wording instead of documenting Opus 4.7 and xhigh

Status: RESOLVED

At https://code.claude.com/docs/en/model-config, lines 163-168: Effort is supported on Opus 4.7, Opus 4.6, and Sonnet 4.6. The available levels depend on the model: followed by | Opus 4.7 | \low\, \medium\, \high\, \xhigh\, \max\ | and | Opus 4.6 and Sonnet 4.6 | \low\, \medium\, \high\, \max\ |.

At https://code.claude.com/docs/en/commands, line 40: ` /effort [level|auto] ... Accepts low, medium, high, xhigh, or max; available levels depend on the model `.

At https://code.claude.com/docs/en/cli-reference, line 61: ` --effort ... Options: low, medium, high, xhigh, max; available levels depend on the model. `

At https://code.claude.com/docs/en/settings, line 191: ` effortLevel ... Accepts "low", "medium", "high", or "xhigh". `

At https://code.claude.com/docs/en/env-vars, line 90: ` CLAUDE_CODE_EFFORT_LEVEL ... Values: low, medium, high, xhigh, max, or auto to use the model default. Available levels depend on the model. `

At https://code.claude.com/docs/en/skills, line 200, https://code.claude.com/docs/en/slash-commands, line 200, and https://code.claude.com/docs/en/sub-agents, line 252: each page now documents xhigh and max as valid effort values, with availability depending on the model.

Verdict: The current command, CLI, settings, environment-variable, skill, slash-command, and subagent documentation no longer uses the reported Opus 4.6-only wording. The docs now describe model-dependent effort support and include xhigh where relevant.

---

Claim 3: The docs did not explain where users see Opus 4.7 xhigh, how /effort changes the speed-versus-intelligence tradeoff, or what xhigh is

Status: RESOLVED

At https://code.claude.com/docs/en/whats-new/2026-w16, line 20: Anthropic's strongest coding model yet is now the default on Max and Team Premium, and available everywhere else from /model. It adds a new xhigh effort level that sits between high and max ... /effort now opens an interactive arrow-key slider ... so you can dial intelligence against speed.

At https://code.claude.com/docs/en/model-config, lines 182-188: the page defines each effort level and describes xhigh as Best results for most coding and agentic tasks. Recommended default on Opus 4.7.

At https://code.claude.com/docs/en/model-config, lines 198-207: the page says users can set effort via /effort, adjust it In /model, and that The effort slider appears in /model when a supported model is selected.

At https://code.claude.com/docs/en/common-workflows, lines 543-549: This is the recommended way to tune the tradeoff between speed and reasoning depth and Opus 4.7 always uses adaptive reasoning and does not support a fixed thinking budget.

Verdict: The current docs now explain that xhigh is an effort level, place it between high and max, describe its tradeoff, and tell users they can access it through /model and /effort.

---

Current State

| Claim | Status |
|-------|--------|
| The model configuration docs still identified Opus 4.6 as the current/latest Opus model | RESOLVED |
| The effort documentation still used Opus 4.6-era wording instead of documenting Opus 4.7 and xhigh | RESOLVED |
| The docs did not explain where users see Opus 4.7 xhigh, how /effort changes the tradeoff, or what xhigh is | RESOLVED |

---

Suggested Fix

N/A - issue has been resolved.

---

References

• URL: https://code.claude.com/docs/en/model-config
• Lines 30-36: Documents the opus alias as the latest Opus model and explicitly maps it to Opus 4.7 on the Anthropic API.
• URL: https://code.claude.com/docs/en/model-config
• Lines 163-176: Documents Opus 4.7 effort support, including xhigh, per-model effort availability, and persistence behavior.
• URL: https://code.claude.com/docs/en/model-config
• Lines 182-207: Defines xhigh, explains the speed/intelligence tradeoff, and documents /effort and /model controls.
• URL: https://code.claude.com/docs/en/commands
• Lines 40-40: Documents /effort with xhigh and model-dependent availability.
• URL: https://code.claude.com/docs/en/cli-reference
• Lines 61-61: Documents --effort with xhigh and model-dependent availability.
• URL: https://code.claude.com/docs/en/settings
• Lines 191-191: Documents effortLevel with xhigh.
• URL: https://code.claude.com/docs/en/env-vars
• Lines 90-90: Documents CLAUDE_CODE_EFFORT_LEVEL with xhigh, max, and auto.
• URL: https://code.claude.com/docs/en/skills
• Lines 200-200: Documents skill frontmatter effort with xhigh and max.
• URL: https://code.claude.com/docs/en/slash-commands
• Lines 200-200: Documents slash-command frontmatter effort with xhigh and max.
• URL: https://code.claude.com/docs/en/sub-agents
• Lines 252-252: Documents subagent frontmatter effort with xhigh and max.
• URL: https://code.claude.com/docs/en/common-workflows
• Lines 543-549: Explains that effort tunes the speed-versus-reasoning-depth tradeoff and distinguishes Opus 4.7 adaptive reasoning behavior.
• URL: https://code.claude.com/docs/en/whats-new/2026-w16
• Lines 20-26: States that Opus 4.7 is available from /model, introduces xhigh, places it between high and max, and shows /effort xhigh.

---

Conclusion & Recommendation

Primary Concern: The issue reported that the docs still reflected Opus 4.6-era model and effort behavior instead of documenting Opus 4.7 and xhigh.

Resolution Status: RESOLVED

Recommendation: CLOSE

The current documentation now identifies Opus 4.7 as the active Opus mapping on the Anthropic API, documents xhigh across the affected effort-related pages, and explains how users access and interpret the new effort level. The reported documentation gap is fixed.

---

This issue has been automatically locked since it was closed and has not had any activity for 7 days. If you're experiencing a similar issue, please file a new issue and reference this one if it's relevant.