From b029954f2d3b86a227554f49f1619bde2ff80543 Mon Sep 17 00:00:00 2001 From: Shiying Fu <30646369+swingfu@users.noreply.github.com> Date: Sun, 21 Sep 2025 20:48:57 -0700 Subject: [PATCH] Clarify cost savings and quality in model choice guide Updated the text to clarify that the model router saves costs with comparable quality instead of no loss in fidelity. --- articles/ai-foundry/foundry-models/how-to/model-choice-guide.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/articles/ai-foundry/foundry-models/how-to/model-choice-guide.md b/articles/ai-foundry/foundry-models/how-to/model-choice-guide.md index bb14d5dad2..df3d28344f 100644 --- a/articles/ai-foundry/foundry-models/how-to/model-choice-guide.md +++ b/articles/ai-foundry/foundry-models/how-to/model-choice-guide.md @@ -88,7 +88,7 @@ _Example Use Cases:_ - High-volume summarization pipelines - Lightweight assistants for internal tools -If you're unsure which model to choose, try [Model Router](https://ai.azure.com/catalog/models/model-router) in Azure AI Foundry for a ready-to-use solution. Developers can use the model router in Foundry Models to maximize the capabilities of the GPT-5 family models (and other models in Foundry Models) while saving up to 60% on inferencing cost with no loss in fidelity. [How to use model router for Azure AI Foundry (preview) – Microsoft Learn](/azure/ai-foundry/openai/how-to/model-router) +If you're unsure which model to choose, try [Model Router](https://ai.azure.com/catalog/models/model-router) in Azure AI Foundry for a ready-to-use solution. Developers can use the model router in Foundry Models to maximize the capabilities of the GPT-5 family models (and other models in Foundry Models) while saving up to 60% on inferencing cost with comparable quality. [How to use model router for Azure AI Foundry (preview) – Microsoft Learn](/azure/ai-foundry/openai/how-to/model-router)