{"version":"2.1.304","anchor":"model-catalog-default-for-the-cc-surface-moved-from-claude-o","canonical_anchor":"model-catalog-default-for-the-cc-surface-moved-from-claude-o","heading":"Bundled default model changes to Opus 5.5 at medium effort","tier":"notice","area":"Models","scope":"individual","heads_up":true,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.304\/e\/model-catalog-default-for-the-cc-surface-moved-from-claude-o","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.304","markdown":"### Bundled default model changes to Opus 5.5 at medium effort\n\nThe model catalog shipped with Claude Code now defaults to claude-opus-5-5 at medium effort instead of claude-opus-5 at high effort\n\n**What**\n\nClaude Code ships with a signed model catalog (a list of models and settings it trusts because it is cryptographically signed). The catalog's default entry for Claude Code has changed:\n\n- before: `claude-opus-5` with thinking effort high\n\n- now: `claude-opus-5-5` with thinking effort medium\n\nThinking effort is how much reasoning the model does before answering.\n\nThe catalog can be refreshed from the server while Claude Code runs, so the copy shipped with the app can be replaced.\n\n**Why**\n\nIf you rely on the default, the model you get and how much it thinks before answering can change, with medium effort as the new default.\n\n- Area: Models\n- Tier: You'll notice\n- Useful: 5\/5\n- Signal: 4\/5\n- Scope: individual\n- Heads-up: yes"}