Merge pull request #3980 from MicrosoftDocs/main

4/8/2025 AM Publish

Author: Taojunshen

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

@@ -146,7 +146,7 @@ DeepSeek family of models includes DeepSeek-R1, which excels at reasoning tasks
 | Model  | Type | Capabilities | 
 | ------ | ---- | --- | 
 | [DeepSeek-V3](https://ai.azure.com/explore/models/deepseek-v3/version/1/registry/azureml-deepseek) | [chat-completion](../model-inference/how-to/use-chat-completions.md?context=/azure/ai-foundry/context/context) | - **Input:** text (131,072 tokens) <br /> - **Output:** text (131,072 tokens) <br />  - **Tool calling:** No <br /> - **Response formats:** Text, JSON |
-| [DeepSeek-R1](https://ai.azure.com/explore/models/deepseek-r1/version/1/registry/azureml-deepseek) | [chat-completion with reasoning content](../model-inference/how-to/use-chat-reasoning.md?context=/azure/ai-foundry/context/context) | - **Input:** text (16,384 tokens) <br /> - **Output:** text (163,840 tokens) <br />  - **Tool calling:** No <br /> - **Response formats:** Text. |
+| [DeepSeek-R1](https://ai.azure.com/explore/models/deepseek-r1/version/1/registry/azureml-deepseek) | [chat-completion with reasoning content](../model-inference/how-to/use-chat-reasoning.md?context=/azure/ai-foundry/context/context) | - **Input:** text (163,840 tokens) <br /> - **Output:** text (163,840 tokens) <br />  - **Tool calling:** No <br /> - **Response formats:** Text. |
 
 For a tutorial on DeepSeek-R1, see [Tutorial: Get started with DeepSeek-R1 reasoning model in Azure AI model inference](../model-inference/tutorials/get-started-deepseek-r1.md?context=/azure/ai-foundry/context/context).
 

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

@@ -109,7 +109,7 @@ DeepSeek family of models includes DeepSeek-R1, which excels at reasoning tasks
 
 | Model  | Type | Tier | Capabilities |
 | ------ | ---- | --- | ------------ |
-| [DeekSeek-R1](https://ai.azure.com/explore/models/deepseek-r1/version/1/registry/azureml-deepseek) | chat-completion <br /> [(with reasoning content)](../how-to/use-chat-reasoning.md) | Global standard | - **Input:** text (16,384 tokens) <br /> - **Output:**  (163,840 tokens) <br /> - **Languages:** `en` and `zh` <br />  - **Tool calling:** No <br /> - **Response formats:** Text. |
+| [DeekSeek-R1](https://ai.azure.com/explore/models/deepseek-r1/version/1/registry/azureml-deepseek) | chat-completion <br /> [(with reasoning content)](../how-to/use-chat-reasoning.md) | Global standard | - **Input:** text (163,840 tokens) <br /> - **Output:**  (163,840 tokens) <br /> - **Languages:** `en` and `zh` <br />  - **Tool calling:** No <br /> - **Response formats:** Text. |
 | [DeekSeek-V3](https://ai.azure.com/explore/models/deepseek-v3/version/1/registry/azureml-deepseek) | chat-completion | Global standard | - **Input:** text (131,072 tokens) <br /> - **Output:**  (131,072 tokens) <br /> - **Languages:** `en` and `zh` <br />  - **Tool calling:** No <br /> - **Response formats:** Text, JSON |
 
 For a tutorial on DeepSeek-R1, see [Tutorial: Get started with DeepSeek-R1 reasoning model in Azure AI model inference](../tutorials/get-started-deepseek-r1.md).

articles/ai-services/openai/how-to/fine-tuning-deploy.md

@@ -397,7 +397,7 @@ Provisioned Managed fine-tuned deployments currently support structured outputs
 
 To create a new deployment, make an HTTP PUT call via the [Deployments - Create or Update REST API](/rest/api/aiservices/accountmanagement/deployments/create-or-update?view=rest-aiservices-accountmanagement-2024-10-01&tabs=HTTP&preserve-view=true). The approach is similar to performing [cross region deployment](#cross-region-deployment) with the following exceptions:
 
-- You must provide a `sku` name of `ProvisionedStandard`.
+- You must provide a `sku` name of `ProvisionedManaged`.
 - The capacity must be declared in PTUs.
 - The `api-version` must be `2024-10-01` or newer.
 - The HTTP method should be `PUT`.
@@ -409,7 +409,7 @@ curl -X PUT "https://management.azure.com/subscriptions/<SUBSCRIPTION>/resourceG
   -H "Authorization: Bearer <TOKEN>" \
   -H "Content-Type: application/json" \
   -d '{
-    "sku": {"name": "ProvisionedStandard", "capacity": 25},
+    "sku": {"name": "ProvisionedManaged", "capacity": 25},
     "properties": {
         "model": {
             "format": "OpenAI",
@@ -432,7 +432,7 @@ curl -X PUT "https://management.azure.com/subscriptions/<SUBSCRIPTION>/resourceG
   -H "Authorization: Bearer <TOKEN>" \
   -H "Content-Type: application/json" \
   -d '{
-    "sku": {"name": "ProvisionedStandard", "capacity": 40},
+    "sku": {"name": "ProvisionedManaged", "capacity": 40},
     "properties": {
         "model": {
             "format": "OpenAI",

articles/ai-services/speech-service/how-to-pronunciation-assessment.md

@@ -13,7 +13,7 @@ ms.custom:
   - ignite-2023
   - build-2024
 ms.topic: how-to
-ms.date: 3/10/2025
+ms.date: 4/7/2025
 ms.author: eur
 zone_pivot_groups: programming-languages-ai-services
 #Customer intent: As a developer, I want to implement pronunciation assessment on spoken language using a technology that works in my environment to gives feedback on accuracy and fluency.
@@ -1105,6 +1105,9 @@ This formula provides a weighted calculation based on the importance of each sco
 
 ## Content assessment
 
+> [!IMPORTANT]
+> Content assessment (preview) via the Speech SDK will be retired in July 2025. Instead, you can use the Azure OpenAI Service to get content assessment results as described in this section.
+
 For some recognized speech, you might also want to get content assessment results for vocabulary, grammar, and topic relevance. You can use a chat model such as Azure OpenAI `gpt-4o` to get the content assessment results. For more information about using chat models, see [Azure OpenAI Service models](../openai/concepts/models.md) and the Azure AI Model Inference API [chat completions reference documentation](/rest/api/aifoundry/model-inference/get-chat-completions/get-chat-completions).
 
 The user and system messages are used to set the context for the chat model. In the following example, the user message contains the essay to be assessed, and the system message provides instructions on how to evaluate the essay.

articles/ai-services/speech-service/includes/release-notes/release-notes-sdk.md

@@ -6,6 +6,9 @@ ms.date: 03/17/2025
 ms.author: eur
 ---
 
+> [!IMPORTANT]
+> Content assessment (preview) via the Speech SDK will be retired in July 2025. Instead, you can use the Azure OpenAI Service to get content assessment results as described in the [content assessment documentation](../../how-to-pronunciation-assessment.md#content-assessment).
+
 ### Speech SDK 1.43: 2025-March release
 
 #### New features:

articles/ai-services/speech-service/releasenotes.md

@@ -1,13 +1,13 @@
 ---
 title: What's new - Speech service
 titleSuffix: Azure AI services
-description: Find out about new releases and features for Azure AI Speech.
+description: Discover the latest updates, features, and improvements in Azure AI Speech, including SDK, CLI, and service releases.
 manager: nitinme
 author: eric-urban
 ms.author: eur
 ms.service: azure-ai-speech
 ms.topic: release-notes
-ms.date: 3/10/2025
+ms.date: 4/7/2025
 ms.custom: references_regions
 # Customer intent: As a developer, I want to learn about new releases and features for Azure AI Speech.
 ---

articles/machine-learning/how-to-deploy-models-serverless.md

@@ -384,16 +384,9 @@ In this section, you create an endpoint with the name **meta-llama3-8b-qwerty**.
     # [Python SDK](#tab/python)
 
     ```python
-    endpoint_name="meta-llama3-8b-qwerty"
-    
-    serverless_endpoint = ServerlessEndpoint(
-        name=endpoint_name,
-        model_id=model_id
-    )
-
-    created_endpoint = client.serverless_endpoints.begin_create_or_update(
-        serverless_endpoint
-    ).result()
+    endpoints = ml_client.online_endpoints.list()
+    for endpoint in endpoints:
+        print(endpoint.name)
     ```
 
     # [ARM](#tab/arm)