{"version":"2.1.228","anchor":"fallback-models-are-reflected-in-the-reported-model","canonical_anchor":"fallback-models-are-reflected-in-the-reported-model","heading":"Fallback models are reflected in the reported model","tier":"notice","area":"Models","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.228\/e\/fallback-models-are-reflected-in-the-reported-model","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.228","markdown":"### Fallback models are reflected in the reported model\n\nIf a request falls back to another model, you now see the model that actually answered.\n\n**What**\n\nWhen a request falls back to a different model mid-stream, the model shown to the client now matches the one that actually answered.\n\n**Details**\n\n- A streamed content block of type \"fallback\" sets the accumulated message's model to the fallback target.\n- The gateway's event re-encoder rewrites the model on the opening `message_start` event when an override model is in play.\n\n**Evidence**\n\n`content_block.type === \"fallback\"`\n\n- Area: Models\n- Tier: You'll notice\n- Useful: 4\/5\n- Signal: 3\/5"}