Merge pull request #7388 from mrbullwinkle/mrb_09_30_2025_freshness_005

[Azure OpenAI] Freshness 005

Author: prmerger-automator[bot]

articles/ai-foundry/openai/how-to/monitor-openai.md

@@ -1,7 +1,7 @@
 ---
 title: Monitor Azure OpenAI in Azure AI Foundry Models
 description: Start here to learn how to use Azure Monitor tools like Log Analytics to capture and analyze metrics and data logs for your Azure OpenAI.
-ms.date: 07/02/2025
+ms.date: 09/30/2025
 ms.custom: horz-monitor, subject-monitoring
 ms.topic: conceptual
 author: mrbullwinkle

articles/ai-foundry/openai/how-to/responses.md

@@ -44,6 +44,7 @@ The responses API is currently available in the following regions:
 
 ### Model support
 
+- `gpt-5-codex`  (Version: `2025-09-11`)
 - `gpt-5` (Version: `2025-08-07`)
 - `gpt-5-mini` (Version: `2025-08-07`)
 - `gpt-5-nano` (Version: `2025-08-07`)

articles/ai-foundry/openai/how-to/structured-outputs.md

@@ -25,6 +25,7 @@ Structured outputs make a model follow a [JSON Schema](https://json-schema.org/o
 
 ## Supported models
 
+- `gpt-5-codex` version `2025-09-11`
 - `gpt-5` version `2025-08-07`
 - `gpt-5-mini` version `2025-08-07`
 - `gpt-5-nano` version `2025-08-07`
@@ -43,7 +44,7 @@ Structured outputs make a model follow a [JSON Schema](https://json-schema.org/o
 
 ## API support
 
-Support for structured outputs was first added in API version `2024-08-01-preview`. It is available in the latest preview APIs as well as the latest GA API: `2024-10-21`.
+Support for structured outputs was first added in API version `2024-08-01-preview`. It is available in the latest preview APIs as well as the latest GA API: `v1`.
 
 
 ::: zone pivot="programming-language-python"

articles/ai-foundry/openai/includes/structured-outputs-python.md

@@ -1,7 +1,7 @@
 ---
 ms.service: azure-ai-openai
 ms.topic: how-to
-ms.date: 05/25/2025
+ms.date: 09/30/2025
 author: mrbullwinkle
 ms.author: mbullwin
 zone_pivot_groups: structured-outputs
@@ -22,20 +22,18 @@ If you are new to using Microsoft Entra ID for authentication see [How to config
 ```python
 import os
 from pydantic import BaseModel
-from openai import AzureOpenAI
+from openai import OpenAI
 from azure.identity import DefaultAzureCredential, get_bearer_token_provider
 
 token_provider = get_bearer_token_provider(
     DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
 )
 
-client = AzureOpenAI(
-  azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT"), 
-  azure_ad_token_provider=token_provider,
-  api_version="2024-10-21"
+client = OpenAI(  
+  base_url = "https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",  
+  api_key=token_provider,
 )
 
-
 class CalendarEvent(BaseModel):
     name: str
     date: str
@@ -108,15 +106,13 @@ pip install openai pydantic --upgrade
 ```python
 import os
 from pydantic import BaseModel
-from openai import AzureOpenAI
+from openai import OpenAI
 
-client = AzureOpenAI(
-  azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT"), 
-  api_key=os.getenv("AZURE_OPENAI_API_KEY"),  
-  api_version="2024-10-21"
+client = OpenAI(
+  base_url = "https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",  
+  api_key=os.getenv("AZURE_OPENAI_API_KEY")  
 )
 
-
 class CalendarEvent(BaseModel):
     name: str
     date: str
@@ -193,15 +189,17 @@ Structured Outputs for function calling can be enabled with a single parameter,
 from enum import Enum
 from typing import Union
 from pydantic import BaseModel
-import openai
-from openai import AzureOpenAI
+from openai import OpenAI
+from azure.identity import DefaultAzureCredential, get_bearer_token_provider
 
-client = AzureOpenAI(
-  azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT"), 
-  api_key=os.getenv("AZURE_OPENAI_API_KEY"),  
-  api_version="2024-10-21"
+token_provider = get_bearer_token_provider(
+    DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
 )
 
+client = OpenAI(  
+  base_url = "https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",  
+  api_key=token_provider,
+)
 
 class GetDeliveryDate(BaseModel):
     order_id: str
@@ -229,14 +227,14 @@ from enum import Enum
 from typing import Union
 from pydantic import BaseModel
 import openai
-from openai import AzureOpenAI
+from openai import OpenAI
 
-client = AzureOpenAI(
-  azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT"), 
-  api_key=os.getenv("AZURE_OPENAI_API_KEY"),  
-  api_version="2024-10-21"
+client = OpenAI(
+  base_url = "https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",  
+  api_key=os.getenv("AZURE_OPENAI_API_KEY")  
 )
 
+
 class GetDeliveryDate(BaseModel):
     order_id: str
 

articles/ai-foundry/openai/includes/structured-outputs-rest.md

@@ -12,10 +12,11 @@ zone_pivot_groups: structured-outputs
 `response_format` is set to `json_schema` with `strict: true` set.
 
 ```bash
-curl -X POST  https://YOUR_RESOURCE_NAME.openai.azure.com/openai/deployments/YOUR_MODEL_DEPLOYMENT_NAME/chat/completions?api-version=2024-10-21 \
+curl -X POST  https://YOUR_RESOURCE_NAME.openai.azure.com/openai/v1/chat/completions \
   -H "api-key: $AZURE_OPENAI_API_KEY" \
   -H "Content-Type: application/json" \
     -d '{
+        "model": "YOUR_MODEL_DEPLOYMENT_NAME",
         "messages": [
                 {"role": "system", "content": "Extract the event information."},
                 {"role": "user", "content": "Alice and Bob are going to a science fair on Friday."}
@@ -85,10 +86,11 @@ Output:
 ## Function calling with structured outputs
 
 ```bash
-curl -X POST  https://YOUR_RESOURCE_NAME.openai.azure.com/openai/deployments/YOUR_MODEL_DEPLOYMENT_NAME/chat/completions?api-version=2024-10-21 \
+curl -X POST  https://YOUR_RESOURCE_NAME.openai.azure.com/openai/v1/chat/completions \
   -H "api-key: $AZURE_OPENAI_API_KEY" \
   -H "Content-Type: application/json" \
   -d '{
+  "model": "YOUR_MODEL_DEPLOYMENT_NAME",
   "messages": [
     {
       "role": "system",