@@ -49,9 +49,6 @@ To request quota increases for these models, submit a request at [https://aka.ms
 | usgovarizona  | ✅ | - | - | ✅ |
 | usgovvirginia | ✅ | - | - | ✅ |
 
-> [!IMPORTANT]
-> Reserved Instance Provisioned Deployments are now available in Azure Government as of May 2025. Refer to [Provisioned Managed Offering in Azure Government](./concepts/gov-provisioned.md) for more details.
-
 <br>
 
 ## Azure OpenAI features

@@ -87,15 +87,15 @@ For more information on how to manage model upgrades and migrations for provisio
 > [!NOTE]
 > Not all models go through a deprecation period prior to retirement. Some models/versions only have a retirement date.
 >
-> **Fine-tuned models** are subject to the same deprecation and retirement schedule as their equivalent base model.
+> **Fine-tuned models** are subject to a [different](#fine-tuned-models) deprecation and retirement schedule from their equivalent base model.
 
 These models are currently available for use in Azure OpenAI.
 
 | Model                     | Version         | Retirement date                    | Replacement model                    |
 | --------------------------|-----------------|------------------------------------|--------------------------------------|
 | `computer-use-preview`    | 2025-03-11      | No earlier than June 11, 2025      |                                      |
 | `dall-e-3`                | 3               | No earlier than June 30, 2025      |                                      |
-| `gpt-35-turbo-16k`        | 0613            | April, 30, 2025                    | `gpt-4.1-mini` version: `2025-04-14` |
+| `gpt-35-turbo-16k`        | 0613            | April  30, 2025                    | `gpt-4.1-mini` version: `2025-04-14` |
 | `gpt-35-turbo`            | 1106            | No earlier than July 16, 2025      | `gpt-4.1-mini` version: `2025-04-14` |
 | `gpt-35-turbo`            | 0125            | No earlier than July 16, 2025      | `gpt-4.1-mini` version: `2025-04-14` |
 | `gpt-4`<br>`gpt-4-32k`    | 0314            | June 6, 2025                       | `gpt-4o` version: `2024-11-20`       |
@@ -130,11 +130,30 @@ We'll notify all customers with these preview deployments at least 30 days befor
 > [!TIP]
 > **Will a model upgrade happen if the new model version is not yet available in that region?**
 >
-> Yes, even in cases where the latest model version is not yet available in a region, we will automatically upgrade deployments during the scheduled upgrade window. For more information, see [Azure OpenAI model versions](/azure/ai-services/openai/concepts/model-versions#will-a-model-upgrade-happen-if-the-new-model-version-is-not-yet-available-in-that-region).
+> Yes, even in cases where the latest model version is not yet available in a region, we'll automatically upgrade deployments during the scheduled upgrade window. For more information, see [Azure OpenAI model versions](/azure/ai-services/openai/concepts/model-versions#will-a-model-upgrade-happen-if-the-new-model-version-is-not-yet-available-in-that-region).
 
 > [!IMPORTANT]
 > Vision enhancements preview features including Optical Character Recognition (OCR), object grounding, video prompts will be retired and no longer available once `gpt-4` Version: `vision-preview` is upgraded to `turbo-2024-04-09`. If you're currently relying on any of these preview features, this automatic model upgrade will be a breaking change.
 
+## Fine-tuned models
+
+Fine-tuned models retire in two phases: training and deployment.
+
+All fine-tuned models follow their equivalent base model for **training** retirement. Once retired, a given model is no longer available for fine tuning.
+
+For fine-tuned models made generally available since `gpt-4o-2024-08-06`, **deployment** retirement occurs 1 year after **training** retirement. At deployment retirement, inference and deployment returns error responses.
+
+| Model            | Version     | Training retirement date  | Deployment retirement date       |
+| -----------------|-------------|---------------------------|----------------------------------|
+| `gpt-35-turbo`   | 1106        | At base model retirement  | At training retirement           |
+| `gpt-35-turbo`   | 0125        | At base model retirement  | At training retirement           |
+| `gpt-4o`         | 2024-08-06  | At base model retirement  | One year after training retirement |
+| `gpt-4o-mini`    | 2024-07-18  | At base model retirement  | One year after training retirement |
+| `gpt-4.1`        | 2025-04-14  | At base model retirement  | One year after training retirement |
+| `gpt-4.1-mini`   | 2025-04-14  | At base model retirement  | One year after training retirement |
+| `gpt-4.1-nano`   | 2025-04-14  | At base model retirement  | One year after training retirement |
+| `o4-mini`        | 2025-04-16  | At base model retirement  | One year after training retirement |
+
 ## Default model versions
 
 | Model | Current default version | New default version | Default upgrade date |

@@ -54,7 +54,7 @@ Model router doesn't process audio input.
 
 ## Billing information
 
-When you use model router, you're only billed for the use of the underlying models as they're recruited to respond to prompts. The model routing function itself doesn't incur any extra charges.
+When you use model router today, you're only billed for the use of the underlying models as they're recruited to respond to prompts: the model routing function itself doesn't incur any extra charges. Starting August 1, the model router usage will be charged as well.
 
 You can monitor the costs of your model router deployment in the Azure portal.
 

@@ -98,7 +98,7 @@ To run the quickstart, follow these steps:
     var speechFilePath = "YOUR_AUDIO_FILE_PATH";
     
     AzureOpenAIClient openAIClient = new AzureOpenAIClient(endpoint, credentials);
-    AudioClient = openAIClient.GetAudioClient(deploymentName);
+    AudioClient audioClient = openAIClient.GetAudioClient(deploymentName);
     
     var result = await audioClient.GenerateSpeechAsync(
                     "the quick brown chicken jumped over the lazy dogs");

@@ -86,7 +86,7 @@ The total number of tokens processed in a given request depends on the length of
  
 #### Image tokens
 
-Azure OpenAI's image processing capabilities with GPT-4o, GPT-4o mini, and GPT-4 Turbo with Vision models uses image tokenization to determine the total number of tokens consumed by image inputs. The number of tokens consumed is calculated based on two main factors: the level of image detail (low or high) and the image’s dimensions. Here's how token costs are calculated:
+Azure OpenAI's image processing capabilities with GPT-4o, GPT-4o-mini, and GPT-4 Turbo with Vision models uses image tokenization to determine the total number of tokens consumed by image inputs. The number of tokens consumed is calculated based on two main factors: the level of image detail (low or high) and the image’s dimensions. Here's how token costs are calculated:
 
 - **Low resolution mode**
   - Low detail allows the API to return faster responses for scenarios that don't require high image resolution analysis. The tokens consumed for low detail images are: