{"version":"2.1.293","anchor":"model-list-entries-gain-maxeffort-cap","canonical_anchor":"model-list-entries-gain-maxeffort-cap","heading":"Model list entries can cap the highest effort level offered","tier":"notice","area":"Effort","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.293\/e\/model-list-entries-gain-maxeffort-cap","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.293","markdown":"### Model list entries can cap the highest effort level offered\n\nEach model in the model list can now set maxEffort, the highest reasoning effort level offered for it\n\n**Unclear.** It is not clear whether the cap is applied anywhere other than Claude Desktop.\n\n**What**\n\nEach entry in the model list can now carry a `maxEffort` setting. Effort is how much reasoning the model is asked to do. The setting works like this:\n\n- Effort levels above `maxEffort` are hidden and never requested by Claude Desktop.\n\n- An unrecognised value caps the model at low.\n\n- When two spellings of the same model with 1M-token context are merged, the lower `maxEffort` is kept.\n\n**Why**\n\nAdministrators can limit how much reasoning effort each model is allowed to use.\n\n- Area: Effort\n- Tier: You'll notice\n- Useful: 4\/5\n- Signal: 3\/5\n- Scope: individual\n- Heads-up: no"}