Merge pull request #3998 from mrbullwinkle/mrb_04_08_2025_quota_capacity_updates

[Azure OpenAI] Add info on capacity API

Author: prmerger-automator[bot]

articles/ai-services/openai/quotas-limits.md

@@ -55,8 +55,6 @@ The following sections provide you with a quick guide to the default quotas and
 
 <sup>1</sup> Our current APIs allow up to 10 custom headers, which are passed through the pipeline, and returned. Some customers now exceed this header count resulting in HTTP 431 errors. There's no solution for this error, other than to reduce header volume. **In future API versions we will no longer pass through custom headers**. We recommend customers not depend on custom headers in future system architectures.
 
-## Regional quota limits
-
 > [!NOTE]
 > Quota limits are subject to change. 
 
@@ -274,6 +272,45 @@ Quota increase requests can be submitted via the [quota increase request form](h
 
 For other rate limits, [submit a service request](../cognitive-services-support-options.md?context=/azure/ai-services/openai/context/context).
 
+## Regional quota capacity limits
+
+You can view quota availability by region for your subscription in the [Azure AI Foundry portal](https://ai.azure.com/resource/quota).
+
+Alternatively to view quota capacity by region for a specific model/version you can query the [capacity API](/rest/api/aiservices/accountmanagement/model-capacities/list) for your subscription. Provide a `subscriptionId`, `model_name`, and `model_version` and the API will return the available capacity for that model across all regions, and deployment types for your subscription.
+
+> [!NOTE]
+> Currently both the Azure AI Foundry portal and the capacity API will return quota/capacity information for models that are [retired](./concepts/model-retirements.md) and no longer available.
+
+[API Reference](/rest/api/aiservices/accountmanagement/model-capacities/list)
+
+```python
+import requests
+import json
+from azure.identity import DefaultAzureCredential
+
+subscriptionId = "Replace with your subscription ID" #replace with your subscription ID
+model_name = "gpt-4o"     # Example value, replace with model name
+model_version = "2024-08-06"   # Example value, replace with model version
+
+token_credential = DefaultAzureCredential()
+token = token_credential.get_token('https://management.azure.com/.default')
+headers = {'Authorization': 'Bearer ' + token.token}
+
+url = f"https://management.azure.com/subscriptions/{subscriptionId}/providers/Microsoft.CognitiveServices/modelCapacities"
+params = {
+    "api-version": "2024-06-01-preview",
+    "modelFormat": "OpenAI",
+    "modelName": model_name,
+    "modelVersion": model_version
+}
+
+response = requests.get(url, params=params, headers=headers)
+model_capacity = response.json()
+
+print(json.dumps(model_capacity, indent=2))
+
+```
+
 ## Next steps
 
 Explore how to [manage quota](./how-to/quota.md) for your Azure OpenAI deployments.

articles/ai-services/openai/whats-new.md

@@ -771,7 +771,7 @@ Azure OpenAI Service now supports speech to text APIs powered by OpenAI's Whispe
 
 ### Regional quota limits increases
 
-- Increases to the max default quota limits for certain models and regions. Migrating workloads to [these models and regions](./quotas-limits.md#regional-quota-limits) will allow you to take advantage of higher Tokens per minute (TPM).  
+- Increases to the max default quota limits for certain models and regions. Migrating workloads to [these models and regions](./quotas-limits.md) will allow you to take advantage of higher Tokens per minute (TPM).  
 
 ## August 2023