[{"data":1,"prerenderedAt":7},["ShallowReactive",2],{"docs-changelog\u002F2026-10-25":3,"docs-tabs-changelog\u002F2026-10-25":6},{"content":4,"lastmod":5},"# API changes: October 25, 2026\n\n[← Changelog](\u002Fdocs\u002Fchangelog) · [October 2026](\u002Fdocs\u002Fchangelog\u002F2026-10)\n\n### NEW-1025-1: preview and connect models to a key of any provider\n\n[GET \u002Fv1\u002Fai\u002Fcredentials\u002F:id\u002Favailable-models](\u002Fdocs\u002Fai\u002Fcredentials\u002Favailable-models) returns the provider's live list and each model's connection state without changing key models. If listing is unavailable, the response remains HTTP 200 with empty `models` and `unavailable.code: provider_list_models_unavailable`.\n\n[POST \u002Fv1\u002Fai\u002Fcredentials\u002F:id\u002Fmodels](\u002Fdocs\u002Fai\u002Fcredentials\u002Fmodels-add) connects models of any provider. A single request preserves HTTP 201; a duplicate returns `409 already_exists`. The new batch `{ modelIds: [...] }` of up to 100 identifiers returns HTTP 200 with `created` and `skipped` arrays; existing connections are marked `already_connected`. An invalid batch is rejected in full before writing. One key holds at most 1000 models: exceeding this returns `409 key_models_limit`.\n\n[GET \u002Fv1\u002Fai\u002Fcredentials\u002F:id\u002Fmodels](\u002Fdocs\u002Fai\u002Fcredentials\u002Fmodels-list) additionally returns `capabilities`, `maxOutputTokens` and `description`.\n",null,{},1794739485143]