{"version":"2.1.190","anchor":"model-scoped-rate-limits-returned-by-status","canonical_anchor":"model-scoped-rate-limits-returned-by-status","heading":"Model-Scoped Rate Limits Returned by \/status","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.190\/e\/model-scoped-rate-limits-returned-by-status","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.190","markdown":"### Model-Scoped Rate Limits Returned by `\/status`\n\nThe internal status endpoint (used by the IDE extensions and the API `get_init_params` call) now includes a `model_scoped` array inside the `rate_limits` object when the server emits per-model windows. Each entry has:\n\n- `display_name` \u2014 server-supplied label for the model bucket (e.g. \"Fable\")\n- `utilization` \u2014 fraction of the weekly window consumed, or null\n- `resets_at` \u2014 ISO-8601 timestamp of window reset, or null\n\nThis field is additive: it appears only when the server returns per-model data and the list is non-empty. It gives integrators visibility into Fable 5 usage separate from the aggregate weekly limit.\n\n**Evidence**\n\nnew schema field (search for `\"Per-model weekly windows from the server limits[] array\"` or `\"model_scoped projection failed:\"`)"}