{"version":"2.1.281","anchor":"model-catalog-comparison-now-covers-default-output-tokens-an","canonical_anchor":"model-catalog-comparison-now-covers-default-output-tokens-an","heading":"Model catalog comparison now covers default output tokens and effort","tier":"internal","area":"Models","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.281\/e\/model-catalog-comparison-now-covers-default-output-tokens-an","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.281","markdown":"### Model catalog comparison now covers default output tokens and effort\n\nClaude Code now checks its default output tokens and default effort against the server's model catalog and reports mismatches\n\n**What**\n\nClaude Code now reads `runtime.default_output_tokens` and `runtime.default_effort` from the server's model catalog, which is the list of models the server offers. It records its own values and compares the two, noting these things:\n\n- The default output tokens (the usual length limit for a reply), and whether that default was requested.\n\n- The default effort, and whether it is pinned above what the server offers.\n\n- Whether the server supplied each value, and whether it matches the local one.\n\nThe comparison report now includes `default_output`, plus `default_effort_old` and `default_effort_new` when the effort differs.\n\nModels can also be marked `rejects_disabled_thinking`. For those models, turning thinking off is refused with \"Thinking can't be turned off for this model\". There is also new handling for the `showThinkingSummaries` setting, and a check for first-party entitlement. Context-window lookups now work from a single resolved model record.\n\n**Why**\n\nIf you try to turn thinking off on a model that requires it, you now get a clear refusal. The comparison reports show where Claude Code's defaults and the server's disagree.\n\n- Area: Models\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 2\/5"}