Merge pull request #5992 from MicrosoftDocs/main

Auto Publish – main to live - 2025-07-11 17:03 UTC

Author: learn-build-service-prod[bot]

articles/ai-foundry/.openpublishing.redirection.ai-studio.json

@@ -110,6 +110,11 @@
             "redirect_url": "/azure/ai-foundry/how-to/data-add",
             "redirect_document_id": true
           },
+          {
+            "source_path_from_root": "/articles/ai-foundry/concepts/models-featured.md",
+            "redirect_url": "/azure/ai-foundry/concepts/models-inference-examples",
+            "redirect_document_id": false
+          },
           {
             "source_path_from_root": "/articles/ai-foundry/model-inference/reference/api-version-updates.md",
             "redirect_url": "/rest/api/aifoundry/modelinference",

articles/ai-foundry/concepts/models-featured.md

@@ -26,16 +26,15 @@ AI Foundry Models is part of Azure AI Foundry, and users can access the service
 
 You can get access to the key model providers in the industry. Explore the following model families available:
 
-- [AI21 Labs](concepts/models.md#ai21-labs)
 - [Azure OpenAI](concepts/models.md#azure-openai)
 - [Cohere](concepts/models.md#cohere)
 - [Core42](concepts/models.md#core42)
-- [DeepSeek](concepts/models.md#deepseek)
+- [DeepSeek](concepts/models.md#deepseek-models-sold-directly-by-azure)
 - [Meta](concepts/models.md#meta)
 - [Microsoft](concepts/models.md#microsoft)
 - [Mistral AI](concepts/models.md#mistral-ai)
 - [NTT Data](concepts/models.md#ntt-data)
-- [xAI](concepts/models.md#xai)
+- [xAI](concepts/models.md#xai-models-sold-directly-by-azure)
 
 To see details for each model including language, types, and capabilities, see [Models](../model-inference/concepts/models.md) article.
 

articles/ai-foundry/concepts/models-inference-examples.md

@@ -33,7 +33,7 @@ Three top-level fields: `input`, `preferred_output` and `non_preferred_output`
 ```json
 {  
   "input": {  
-    "messages": {"role": "system", "content": ...},  
+    "messages": [{"role": "system", "content": ...}],  
     "tools": [...],  
     "parallel_tool_calls": true  
   },  

articles/ai-foundry/foundry-models/concepts/models.md

@@ -26,13 +26,15 @@ ms.custom:
 | `gpt-4o` (2024-08-06) | East US2 <br> North Central US <br> Sweden Central | - | Input: 128,000 <br> Output: 16,384  <br> Training example context length: 65,536 | Oct 2023 | Text & Vision to Text |
 | `gpt-4.1` (2025-04-14) | North Central US <br> Sweden Central | ✅ | Input: 128,000 <br> Output: 16,384 <br> Training example context length: 65,536 | May 2024 | Text & Vision to Text |
 | `gpt-4.1-mini` (2025-04-14) | North Central US <br> Sweden Central | ✅ | Input: 128,000 <br> Output: 16,384 <br> Training example context length: 65,536 | May 2024 | Text to Text |
-| `gpt-4.1-nano` (2025-04-14) | North Central US <br> Sweden Central | - | Input: 128,000 <br> Output: 16,384 <br> Training example context length: 32,768 | May 2024 | Text to Text |
+| `gpt-4.1-nano` (2025-04-14) | North Central US <br> Sweden Central | ✅ | Input: 128,000 <br> Output: 16,384 <br> Training example context length: 32,768 | May 2024 | Text to Text |
 | `o4-mini` (2025-04-16) | East US2 <br> Sweden Central | - | Input: 128,000 <br> Output: 16,384 <br> Training example context length: 65,536 | May 2024 | Text to Text |
 
 > [!NOTE]
 > **Global** training (in Public Preview) provides [more affordable](https://aka.ms/aoai-pricing) training per-token, but does not offer [data residency](https://aka.ms/data-residency). It is currently available to Azure OpenAI resources in the following regions, with more regions coming soon:
 >- Australia East
 >- Brazil South
+>- Canada Central
+>- Canada East
 >- East US
 >- East US2
 >- France Central
@@ -42,10 +44,11 @@ ms.custom:
 >- Korea Central
 >- North Central US
 >- Norway East
->- Poland Central
+>- Poland Central _(no 4.1-nano support)_
 >- Southeast Asia
 >- South Africa North
 >- South Central US
+>- South India
 >- Spain Central
 >- Sweden Central
 >- Switzerland West

articles/ai-foundry/foundry-models/overview.md

@@ -47,6 +47,7 @@ The following sections provide you with a quick guide to the default quotas and
 | Maximum number of Provisioned throughput units per deployment | 100,000 |
 | Max files per Assistant/thread | 10,000 when using the API or [Azure AI Foundry portal](https://ai.azure.com/?cid=learnDocs).|
 | Max file size for Assistants & fine-tuning | 512 MB<br/><br/>200 MB via [Azure AI Foundry portal](https://ai.azure.com/?cid=learnDocs) |
+| Max file upload requests per resource | 30 requests per second |
 | Max size for all uploaded files for Assistants |200 GB |
 | Assistants token limit | 2,000,000 token limit |
 | GPT-4o and GPT-4.1 max images per request (# of images in the messages array/conversation history) | 50 |

articles/ai-foundry/openai/how-to/fine-tuning-direct-preference-optimization.md

@@ -112,8 +112,8 @@ items:
         href: how-to/deploy-models-serverless-availability.md
       - name: Guardrails & controls for serverless API 
         href: concepts/model-catalog-content-safety.md
-      - name: Models available for serverless API
-        href: concepts/models-featured.md
+      - name: Inference examples for serverless deployments
+        href: concepts/models-inference-examples.md
       - name: Gretel Navigator model
         href: how-to/deploy-models-gretel-navigator.md
       - name: Mistral-7B and Mixtral models

articles/ai-foundry/openai/includes/fine-tune-models.md

@@ -6,9 +6,9 @@ services: machine-learning
 ms.service: azure-machine-learning
 ms.subservice: mldata
 ms.topic: concept-article
-author: fbsolo-ms1 
-ms.author: franksolomon 
-ms.reviewer: yogipandey
+author: s-polly
+ms.author: scottpolly 
+ms.reviewer: sooryar
 ms.date: 09/06/2024
 ms.custom: cliv2, sdkv2, build-2023
 #Customer intent: As a full-stack machine learning pro, I want to use Apache Spark in Azure Machine Learning.