{"version":"2.1.311","anchor":"rate-limit-checkpoint-and-rewindultrathink-changes","canonical_anchor":"rate-limit-checkpoint-and-rewindultrathink-changes","heading":"Typing ultrathink in a prompt can raise reasoning effort to xhigh","tier":"use","area":"Effort","scope":"individual","heads_up":true,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.311\/e\/rate-limit-checkpoint-and-rewindultrathink-changes","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.311","markdown":"### Typing ultrathink in a prompt can raise reasoning effort to xhigh\n\nA prompt containing ultrathink now sets reasoning effort to xhigh for that request when the model you are using qualifies\n\n**Unclear.** Which models qualify, and what other conditions must hold, is not stated.\n\n**What**\n\nWhen you submit a prompt that contains the word ultrathink, and the model you are using qualifies, Claude Code now sets the reasoning effort for that request to `xhigh`. Reasoning effort is how much thinking the model does before it answers. Claude Code also records that this boost happened.\n\n**Why**\n\nIn practice, including ultrathink in a prompt gets that one request the higher xhigh effort level without changing any setting.\n\n- Area: Effort\n- Names: `ultrathink`\n- Tier: Use it now\n- Useful: 4\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: yes"}