{"version":"2.1.251","anchor":"effort-cap-when-thinking-is-off-tied-to-a-specific-model","canonical_anchor":"effort-cap-when-thinking-is-off-tied-to-a-specific-model","heading":"Effort cap when thinking is off, tied to a specific model","tier":"internal","area":"Models","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.251\/e\/effort-cap-when-thinking-is-off-tied-to-a-specific-model","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.251","markdown":"### Effort cap when thinking is off, tied to a specific model\n\nSome models cap reasoning effort when thinking is off, matched by name or capability.\n\n**What**\n\nA check now identifies models that cap reasoning effort when thinking is disabled, matching `claude-opus-5` by name or any model whose capability list carries a `thinking_disabled_effort_cap` entry.\n\n**Details**\n\n- The capability lookup means the cap can apply to future models without a code change.\n- Reworked in this release rather than introduced.\n\n**Evidence**\n\n`claude-opus-5`\n\n- Area: Models\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 5\/5"}