Context & Reasoning/Extended Reasoning & Effort
Advanced8 min

Effort Levels — The Reasoning Slider

Effort levels are a session-wide reasoning depth control — separate from ultrathink's per-prompt override. Opus 4.7 introduced xhigh as the new default, sitting between high and max. Understanding the five levels prevents both under-spending on hard problems and over-spending on easy ones.

Quick Reference

  • Five levels: low, medium, high, xhigh, max
  • xhigh: new tier in Opus 4.7 — Opus 4.7 defaults to xhigh, not high
  • Opus 4.6 / Sonnet 4.6 on Max/Enterprise/Team: defaults to high
  • Opus 4.6 / Sonnet 4.6 on Pro: defaults to medium
  • Other models silently fall back to high if xhigh is requested but not supported
  • /effort command: interactive arrow-key slider (April 2026) — no argument needed
  • CLAUDE_CODE_EFFORT_LEVEL env var: persistent default across sessions
  • Effort is model-calibrated: high on Haiku ≠ high on Opus 4.7

The Five Effort Levels

Effort levels control reasoning depth, agentic persistence, and how aggressively Claude pursues tool calls before responding. They are not fixed token budgets — they are calibrated to each model's capacity and scale dynamically based on the complexity of the current turn.

LevelSymbolDefault forUse case
lowHigh-volume tasks, quick lookups, simple classification — speed and cost over depth
mediumOpus 4.6/Sonnet 4.6 on ProBalanced performance — solid results without full token expenditure
highOpus 4.6/Sonnet 4.6 on Max/Team/EnterpriseDeep reasoning for complex tasks — the baseline for serious implementation work
xhighOpus 4.7 (all plans)Extended exploration, repeated tool calling, complex agentic coding — sweet spot between performance and cost
maxMaximum reasoning, no token constraint — only for the hardest architectural decisions
xhigh Is New in Opus 4.7

xhigh was introduced with Opus 4.7 in April 2026. It sits between high and max, and is specifically designed for the extended agentic work that Opus 4.7 excels at — complex multi-step coding, repeated tool calling, exploration before implementation. Anthropic describes it as 'the compelling sweet spot between performance and token expenditure.'