{"version":"2.1.290","anchor":"effort-setting-is-now-held-by-a-model-specific-value","canonical_anchor":"effort-setting-is-now-held-by-a-model-specific-value","heading":"Effort setting can be held back for some models","tier":"notice","area":"Effort","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.290\/e\/effort-setting-is-now-held-by-a-model-specific-value","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.290","markdown":"### Effort setting can be held back for some models\n\nClaude Code can now leave the effort level unset for some models instead of taking it from your settings\n\n**Unclear.** What the model-specific hold value is and which models have one is unclear.\n\n**What**\n\nEffort is how much thinking the model puts into a reply. When working out the effort level, Claude Code can now leave it unset for a model that has a model-specific hold value, instead of taking it from your settings. Taking the default from the settings table directly now also depends on a condition.\n\n**Why**\n\nThe effort shown or applied for some models may differ from what your settings say.\n\n- Area: Effort\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 3\/5\n- Scope: individual\n- Heads-up: no"}