{"version":"2.1.323","anchor":"output-token-default-derivation-changed","canonical_anchor":"output-token-default-derivation-changed","heading":"Default output length and effort now come from a per-model value","tier":"notice","area":"Models","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323\/e\/output-token-default-derivation-changed","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323","markdown":"### Default output length and effort now come from a per-model value\n\nClaude Code now works out the default output token limit and the default effort from a value set for each model\n\n**Unclear.** It is not clear whether the actual default limits are different for any model.\n\n**What**\n\nOutput tokens are the units that measure how long a reply from the model can be. Claude Code now works out the default limit on output tokens, and the default effort level, from a value set for each model. The older way of calculating these defaults has been removed.\n\n**Why**\n\nThe default maximum reply length could be different for some models.\n\n- Area: Models\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 3\/5\n- Scope: individual\n- Heads-up: no"}