@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI
 description: Learn about the model deprecations and retirements in Azure OpenAI.
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 02/28/2025
+ms.date: 03/11/2025
 ms.custom: 
 manager: nitinme
 author: mrbullwinkle
@@ -103,7 +103,7 @@ These models are currently available for use in Azure OpenAI Service.
 | `gpt-4` | 1106-preview | To be upgraded to **`gpt-4o` version: `2024-11-20`**, starting no sooner than March 10, 2025 **<sup>1</sup>** <br>Retirement date: April 02, 2025  | `gpt-4o`|
 | `gpt-4` | 0125-preview |To be upgraded to **`gpt-4o` version: `2024-11-20`**, starting no sooner than March 10, 2025 **<sup>1</sup>** <br>Retirement date: April 02, 2025  | `gpt-4o` |
 | `gpt-4` | vision-preview | To be upgraded to **`gpt-4o` version: `2024-11-20`**, starting no sooner than March 10, 2025  **<sup>1</sup>** <br>Retirement date: April 02, 2025 | `gpt-4o`|
-| `gpt-4o` | 2024-05-13 | No earlier than May 20, 2025 <br><br>Deployments set to [**Auto-update to default**](/azure/ai-services/openai/how-to/working-with-models?tabs=powershell#auto-update-to-default) will be automatically upgraded to version: `2024-08-06`, starting on February 13, 2025. | |
+| `gpt-4o` | 2024-05-13 | No earlier than June 30, 2025 <br><br>Deployments set to [**Auto-update to default**](/azure/ai-services/openai/how-to/working-with-models?tabs=powershell#auto-update-to-default) will be automatically upgraded to version: `2024-08-06`, starting on March 17, 2025. | |
 | `gpt-4o` | 2024-08-06 | No earlier than August 6, 2025  | |
 | `gpt-4o` | 2024-11-20 | No earlier than November 20, 2025  | |
 | `gpt-4o-mini` | 2024-07-18 | No earlier than July 18, 2025  | |
@@ -113,8 +113,8 @@ These models are currently available for use in Azure OpenAI Service.
 | `o1` | 2024-12-17 | No earlier than December 17, 2025 | |
 | `text-embedding-ada-002` | 2 | No earlier than October 3, 2025 | `text-embedding-3-small` or `text-embedding-3-large` |
 | `text-embedding-ada-002` | 1 | No earlier than October 3, 2025 | `text-embedding-3-small` or `text-embedding-3-large` |
-| `text-embedding-3-small` | | No earlier than October 3, 2025 | |
-| `text-embedding-3-large` | | No earlier than October 3, 2025 | |
+| `text-embedding-3-small` | | No earlier than January 25, 2026 | |
+| `text-embedding-3-large` | | No earlier than January 25, 2026 | |
 
  **<sup>1</sup>** We'll notify all customers with these preview deployments at least 30 days before the start of the upgrades. We'll publish an upgrade schedule detailing the order of regions and model versions that we'll follow during the upgrades, and link to that schedule from here.
 

@@ -7,7 +7,7 @@ author: aapowell
 ms.author: aapowell
 ms.service: azure-ai-openai
 ms.topic: include
-ms.date: 3/10/2025
+ms.date: 3/11/2025
 ---
 
 [Reference documentation](/dotnet/api/overview/azure/ai.openai.assistants-readme?context=/azure/ai-services/openai/context/context) |  [Source code](https://github.com/Azure/azure-sdk-for-net/blob/main/sdk/openai/Azure.AI.OpenAI/src) | [Package (NuGet)](https://www.nuget.org/packages/Azure.AI.OpenAI/)
@@ -62,9 +62,9 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
 
 [!INCLUDE [resource authentication](resource-authentication.md)]
 
-## Create the assistant
+## Run the quickstart
 
-The sample code in this quickstart uses Microsoft Entra ID for the recommended keyless authentication. If you prefer to use an API key, you can replace the `DefaultAzureCredential` object with a `AzureKeyCredential` object. 
+The sample code in this quickstart uses Microsoft Entra ID for the recommended keyless authentication. If you prefer to use an API key, you can replace the `DefaultAzureCredential` object with an `AzureKeyCredential` object. 
 
 #### [Microsoft Entra ID](#tab/keyless)
 
@@ -79,9 +79,9 @@ AzureOpenAIClient openAIClient = new AzureOpenAIClient(new Uri(endpoint), new Az
 ```
 ---
 
-To create an assistant, you need to:
+To run the quickstart, follow these steps:
 
-1. Update the `Program.cs` file with the following code to create an assistant:
+1. Replace the contents of `Program.cs` with the following code and update the placeholder values with your own.
     
     ```csharp
     using Azure;

@@ -7,7 +7,7 @@ ms.service: azure-ai-openai
 ms.topic: include
 author: mrbullwinkle
 ms.author: mbullwin
-ms.date: 11/15/2023
+ms.date: 3/11/2025
 ---
 
 [Source code](https://github.com/Azure/azure-sdk-for-net/blob/main/sdk/openai/Azure.AI.OpenAI/src) | [Package (NuGet)](https://www.nuget.org/packages/Azure.AI.OpenAI/) | [Samples](https://github.com/Azure/azure-sdk-for-net/blob/main/sdk/openai/Azure.AI.OpenAI/tests/Samples)| [Retrieval Augmented Generation (RAG) enterprise chat template](/dotnet/ai/get-started-app-chat-template) |
@@ -60,9 +60,9 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
 
 [!INCLUDE [resource authentication](resource-authentication.md)]
 
-## Add the code for chat completion
+## Run the quickstart
 
-The sample code in this quickstart uses Microsoft Entra ID for the recommended keyless authentication. If you prefer to use an API key, you can replace the `DefaultAzureCredential` object with a `AzureKeyCredential` object. 
+The sample code in this quickstart uses Microsoft Entra ID for the recommended keyless authentication. If you prefer to use an API key, you can replace the `DefaultAzureCredential` object with an `AzureKeyCredential` object. 
 
 #### [Microsoft Entra ID](#tab/keyless)
 
@@ -81,9 +81,9 @@ You can use streaming or non-streaming to get the chat completion. The following
 
 ### Without response streaming
 
-To use the non-streaming method:
+To run the quickstart, follow these steps:
 
-1. Update the `Program.cs` file with the following code:
+1. Replace the contents of `Program.cs` with the following code and update the placeholder values with your own.
 
     ```csharp
     using Azure;
@@ -127,12 +127,13 @@ To use the non-streaming method:
 Assistant: Arrr, ye be askin’ a fine question, matey! Aye, several Azure AI services support customer-managed keys (CMK)! This lets ye take the wheel and secure yer data with encryption keys stored in Azure Key Vault. Services such as Azure Machine Learning, Azure Cognitive Search, and others also offer CMK fer data protection. Always check the specific service's documentation fer the latest updates, as features tend to shift swifter than the tides, aye!
 ```
 
-This will wait until the model has generated its entire response before printing the results. Alternatively, if you want to asynchronously stream the response and print the results, you can replace the contents of *program.cs* with the code in the next example.
+This will wait until the model has generated its entire response before printing the results. Alternatively, if you want to asynchronously stream the response and print the results, you can replace the contents of *Program.cs* with the code in the next example.
 
 ### Async with streaming
 
-To use the streaming method:
-1. Update the `Program.cs` file with the following code:
+To run the quickstart, follow these steps:
+
+1. Replace the contents of `Program.cs` with the following code and update the placeholder values with your own.
 
     ```csharp
     using Azure;

@@ -8,7 +8,7 @@ ms.service: azure-ai-openai
 ms.topic: include
 author: PatrickFarley
 ms.author: pafarley
-ms.date: 06/26/2024
+ms.date: 3/11/2025
 ---
 
 Use this guide to get started generating images with the Azure OpenAI SDK for C#.
@@ -21,83 +21,101 @@ Use this guide to get started generating images with the Azure OpenAI SDK for C#
 - The [.NET 7 SDK](https://dotnet.microsoft.com/download/dotnet/7.0)
 - An Azure OpenAI resource created in a supported region (see [Region availability](/azure/ai-services/openai/concepts/models#model-summary-table-and-region-availability)). For more information, see [Create a resource and deploy a model with Azure OpenAI](../how-to/create-resource.md).
 
+### Microsoft Entra ID prerequisites
 
-## Setup
+For the recommended keyless authentication with Microsoft Entra ID, you need to:
+- Install the [Azure CLI](/cli/azure/install-azure-cli) used for keyless authentication with Microsoft Entra ID.
+- Assign the `Cognitive Services User` role to your user account. You can assign roles in the Azure portal under **Access control (IAM)** > **Add role assignment**.
 
-[!INCLUDE [get-key-endpoint](get-key-endpoint.md)]
+## Set up
 
-[!INCLUDE [environment-variables](environment-variables.md)]
+1. Create a new folder `vision-quickstart` to contain the application and open Visual Studio Code in that folder with the following command:
 
+    ```shell
+    mkdir vision-quickstart && cd vision-quickstart
+    ```
 
-## Create a new .NET Core application
+1. Create a new console application with the following command:
 
-In a console window (such as cmd, PowerShell, or Bash), use the `dotnet new` command to create a new console app with the name `azure-openai-quickstart`. This command creates a simple "Hello World" project with a single C# source file: *Program.cs*.
+    ```shell
+    dotnet new console
+    ```
 
-```dotnetcli
-dotnet new console -n azure-openai-quickstart
-```
+3. Install the [OpenAI .NET client library](https://www.nuget.org/packages/Azure.AI.OpenAI/) with the [dotnet add package](/dotnet/core/tools/dotnet-add-package) command:
 
-Change your directory to the newly created app folder. You can build the application with:
+    ```console
+    dotnet add package Azure.AI.OpenAI --version 1.0.0-beta.6
+    ```
 
-```dotnetcli
-dotnet build
-```
+1. For the **recommended** keyless authentication with Microsoft Entra ID, install the [Azure.Identity](https://www.nuget.org/packages/Azure.Identity) package with:
 
-The build output should contain no warnings or errors.
+    ```console
+    dotnet add package Azure.Identity
+    ```
 
-```output
-...
-Build succeeded.
- 0 Warning(s)
- 0 Error(s)
-...
-```
+1. For the **recommended** keyless authentication with Microsoft Entra ID, sign in to Azure with the following command:
 
-## Install the OpenAI .NET SDK
+    ```console
+    az login
+    ```
 
-Install the client library with:
+## Retrieve resource information
 
-```dotnetcli
-dotnet add package Azure.AI.OpenAI --version 1.0.0-beta.6
-```
+[!INCLUDE [resource authentication](resource-authentication.md)]
 
-## Generate images with DALL-E
+## Run the quickstart
 
-From the project directory, open the *program.cs* file and replace the contents with the following code:
+The sample code in this quickstart uses Microsoft Entra ID for the recommended keyless authentication. If you prefer to use an API key, you can replace the `DefaultAzureCredential` object with an `AzureKeyCredential` object. 
+
+#### [Microsoft Entra ID](#tab/keyless)
 
 ```csharp
-using Azure;
-using Azure.AI.OpenAI;
-using OpenAI.Images;
-using static System.Environment;
-
-string endpoint = GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT");
-string key = GetEnvironmentVariable("AZURE_OPENAI_API_KEY");
-
-AzureOpenAIClient openAIClient = new(
-    new Uri(endpoint),
-    new AzureKeyCredential(key));
-
-// This must match the custom deployment name you chose for your model
-ImageClient chatClient = openAIClient.GetImageClient("dalle-3");
-
-var imageGeneration = await chatClient.GenerateImageAsync(
-        "a happy monkey sitting in a tree, in watercolor",
-        new ImageGenerationOptions()
-        {
-            Size = GeneratedImageSize.W1024xH1024
-        }
-    );
-
-Console.WriteLine(imageGeneration.Value.ImageUri);
+AzureOpenAIClient openAIClient = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential()); 
 ```
 
-Build and run the application from your application directory with these commands:
+#### [API key](#tab/api-key)
 
-```dotnet
-dotnet build
-dotnet run
+```csharp
+AzureOpenAIClient openAIClient = new AzureOpenAIClient(new Uri(endpoint), new AzureKeyCredential(key));
 ```
+---
+
+To run the quickstart, follow these steps:
+
+1. Replace the contents of `Program.cs` with the following code and update the placeholder values with your own.
+
+    ```csharp
+    using Azure;
+    using Azure.AI.OpenAI;
+    using OpenAI.Images;
+    using static System.Environment;
+    
+    string endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? "https://<your-resource-name>.openai.azure.com/";
+    string key = Environment.GetEnvironmentVariable("AZURE_OPENAI_API_KEY") ?? "<your-key>";
+    
+    // Use the recommended keyless credential instead of the AzureKeyCredential credential.
+    AzureOpenAIClient openAIClient = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential()); 
+    //AzureOpenAIClient openAIClient = new AzureOpenAIClient(new Uri(endpoint), new AzureKeyCredential(key));
+    
+    // This must match the custom deployment name you chose for your model
+    ImageClient chatClient = openAIClient.GetImageClient("dalle-3");
+    
+    var imageGeneration = await chatClient.GenerateImageAsync(
+            "a happy monkey sitting in a tree, in watercolor",
+            new ImageGenerationOptions()
+            {
+                Size = GeneratedImageSize.W1024xH1024
+            }
+        );
+    
+    Console.WriteLine(imageGeneration.Value.ImageUri);
+    ```
+
+1. Run the application using the `dotnet run` command or the run button at the top of Visual Studio:
+
+    ```dotnetcli
+    dotnet run
+    ```
 
 ## Output
 

@@ -62,7 +62,7 @@ dotnet add package Azure.AI.OpenAI --version 1.0.0-beta.17
 
 ## Create a sample application
 
-From the project directory, open the *program.cs* file and replace with the following code:
+From the project directory, open the *Program.cs* file and replace with the following code:
 
 ```csharp
 using Azure;
@@ -91,7 +91,7 @@ Console.WriteLine($"Chatbot: {completion}");
 > For production, use a secure way of storing and accessing your credentials like [Azure Key Vault](/azure/key-vault/general/overview). For more information about credential security, see the Azure AI services [security](../../security-features.md) article.
 
 ```cmd
-dotnet run program.cs
+dotnet run Program.cs
 ```
 
 ## Output

@@ -7,7 +7,7 @@ manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: include
 ms.custom: references_regions
-ms.date: 01/22/2024
+ms.date: 3/11/2025
 ---
 
 Use this article to get started using the Azure OpenAI .NET SDK to deploy and use the GPT-4 Turbo with Vision model. 
@@ -18,98 +18,109 @@ Use this article to get started using the Azure OpenAI .NET SDK to deploy and us
 - [The .NET 8.0 SDK](https://dotnet.microsoft.com/en-us/download)
 - An Azure OpenAI Service resource with a GPT-4 Turbo with Vision model deployed. See [GPT-4 and GPT-4 Turbo Preview model availability](../concepts/models.md#gpt-4-and-gpt-4-turbo-model-availability) for available regions. For more information about resource creation, see the [resource deployment guide](/azure/ai-services/openai/how-to/create-resource).
 
-## Set up
+### Microsoft Entra ID prerequisites
 
-### Retrieve key and endpoint
+For the recommended keyless authentication with Microsoft Entra ID, you need to:
+- Install the [Azure CLI](/cli/azure/install-azure-cli) used for keyless authentication with Microsoft Entra ID.
+- Assign the `Cognitive Services User` role to your user account. You can assign roles in the Azure portal under **Access control (IAM)** > **Add role assignment**.
 
-To successfully make a call against Azure OpenAI, you need an **endpoint** and a **key**.
+## Set up
 
-|Variable name | Value |
-|--------------------------|-------------|
-| `AZURE_OPENAI_ENDPOINT`               | The service endpoint can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively, you can find the endpoint via the **Deployments** page in Azure AI Foundry portal. An example endpoint is: `https://docs-test-001.openai.azure.com/`. |
-| `AZURE_OPENAI_API_KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either `KEY1` or `KEY2`.|
+1. Create a new folder `vision-quickstart` to contain the application and open Visual Studio Code in that folder with the following command:
 
-Go to your resource in the Azure portal. The **Endpoint and Keys** can be found in the **Resource Management** section. Copy your endpoint and access key as you need both for authenticating your API calls. You can use either `KEY1` or `KEY2`. Always having two keys allows you to securely rotate and regenerate keys without causing a service disruption.
+    ```shell
+    mkdir vision-quickstart && cd vision-quickstart
+    ```
 
-:::image type="content" source="../media/quickstarts/endpoint.png" alt-text="Screenshot of the overview UI for an Azure OpenAI resource in the Azure portal with the endpoint & access keys location highlighted." lightbox="../media/quickstarts/endpoint.png":::
+1. Create a new console application with the following command:
 
+    ```shell
+    dotnet new console
+    ```
 
-## Create the .NET app
+3. Install the [OpenAI .NET client library](https://www.nuget.org/packages/Azure.AI.OpenAI/) with the [dotnet add package](/dotnet/core/tools/dotnet-add-package) command:
 
-1. Create a .NET app using the `dotnet new` command:
+    ```console
+    dotnet add package Azure.AI.OpenAI
+    ```
 
-    ```dotnetcli
-    dotnet new console -n OpenAISpeech
+1. For the **recommended** keyless authentication with Microsoft Entra ID, install the [Azure.Identity](https://www.nuget.org/packages/Azure.Identity) package with:
+
+    ```console
+    dotnet add package Azure.Identity
     ```
 
-1. Change into the directory of the new app:
+1. For the **recommended** keyless authentication with Microsoft Entra ID, sign in to Azure with the following command:
 
-    ```dotnetcli
-    cd OpenAISpeech
+    ```console
+    az login
     ```
 
-## Install the client library
+## Retrieve resource information
 
-Install the [`Azure.OpenAI`](https://www.nuget.org/packages/Azure.AI.OpenAI/) client library:
+[!INCLUDE [resource authentication](resource-authentication.md)]
 
-```dotnetcli
-dotnet add package Azure.AI.OpenAI
-```
+## Run the quickstart
 
-## Passwordless authentication is recommended
+The sample code in this quickstart uses Microsoft Entra ID for the recommended keyless authentication. If you prefer to use an API key, you can replace the `DefaultAzureCredential` object with an `AzureKeyCredential` object. 
 
-Passwordless authentication is more secure than key-based alternatives and is the recommended approach for connecting to Azure services. If you choose to use Passwordless authentication, you'll need to complete the following:
+#### [Microsoft Entra ID](#tab/keyless)
 
-1. Add the [`Azure.Identity`](https://www.nuget.org/packages/Azure.Identity) package.
+```csharp
+AzureOpenAIClient openAIClient = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential()); 
+```
 
-    ```dotnetcli
-    dotnet add package Azure.Identity
-    ```
+#### [API key](#tab/api-key)
 
-1. Assign the `Cognitive Services User` role to your user account. This can be done in the Azure portal on your OpenAI resource under **Access control (IAM)** > **Add role assignment**.
-1. Sign-in to Azure using Visual Studio or the Azure CLI via `az login`.
+```csharp
+AzureOpenAIClient openAIClient = new AzureOpenAIClient(new Uri(endpoint), new AzureKeyCredential(key));
+```
+---
 
-## Update the app code
+To run the quickstart, follow these steps:
 
-1. Replace the contents of `program.cs` with the following code and update the placeholder values with your own.
+1. Replace the contents of `Program.cs` with the following code and update the placeholder values with your own.
 
     ```csharp
     using Azure;
     using Azure.AI.OpenAI;
     using Azure.Identity;
     using OpenAI.Chat; // Required for Passwordless auth
     
-    var endpoint = new Uri("YOUR_AZURE_OPENAI_ENDPOINT");
-    var credentials = new AzureKeyCredential("YOUR_AZURE_OPENAI_KEY");
-    // var credentials = new DefaultAzureCredential(); // Use this line for Passwordless auth
-    var deploymentName = "gpt-4"; // Default name, update with your own if needed
+    string deploymentName = "gpt-4";
     
-    AzureOpenAIClient openAIClient = new AzureOpenAIClient(endpoint, credentials);
+    string endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? "https://<your-resource-name>.openai.azure.com/";
+    string key = Environment.GetEnvironmentVariable("AZURE_OPENAI_API_KEY") ?? "<your-key>";
+    
+    // Use the recommended keyless credential instead of the AzureKeyCredential credential.
+    AzureOpenAIClient openAIClient = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential()); 
+    //AzureOpenAIClient openAIClient = new AzureOpenAIClient(new Uri(endpoint), new AzureKeyCredential(key));
+
     var chatClient = openAIClient.GetChatClient(deploymentName);
     
     var imageUri = "YOUR_IMAGE_URL";
     
-    List<ChatMessage> messages = [
-        new UserChatMessage(
-            ChatMessageContentPart.CreateTextMessageContentPart("Please describe the following image:"),
-            ChatMessageContentPart.CreateImageMessageContentPart(new Uri(imageUri), "image/png"))
-    ];
-    
-    ChatCompletion chatCompletion = await chatClient.CompleteChatAsync(messages);
+    var chatMessages = new List<ChatMessage>
+    {
+        new SystemChatMessage("You are a helpful assistant."),
+        new UserChatMessage($"Describe this picture: {imageUrl}")
+    };
+        
+    ChatCompletion chatCompletion = await chatClient.CompleteChatAsync(chatMessages);
     
     Console.WriteLine($"[ASSISTANT]:");
     Console.WriteLine($"{chatCompletion.Content[0].Text}");
     ```
 
-[!INCLUDE [Azure Key Vault](~/reusable-content/ce-skilling/azure/includes/ai-services/security/microsoft-entra-id-akv-expanded.md)]
-
 1. Run the application using the `dotnet run` command or the run button at the top of Visual Studio:
 
     ```dotnetcli
     dotnet run
     ```
 
-  The app generates an audio file at the location you specified for the `speechFilePath` variable. Play the file on your device to hear the generated audio.
+## Output
+
+The output of the application will be a description of the image you provided in the `imageUri` variable. The assistant will analyze the image and provide a detailed description based on its content.
 
 ## Clean up resources
 

@@ -2,11 +2,10 @@
 ms.topic: include
 manager: nitinme
 ms.service: azure-ai-openai
-ms.topic: include
-ms.date: 09/23/2024
-ms.reviewer: eur
-ms.author: alexwolf
-author: alexwolfmsft
+ms.date: 3/11/2025
+ms.reviewer: alexwolf
+ms.author: eur
+author: eric-urban
 recommendations: false
 ---
 
@@ -16,62 +15,72 @@ recommendations: false
 - An Azure OpenAI resource with a Whisper model deployed in a [supported region](../concepts/models.md#whisper-models). For more information, see [Create a resource and deploy a model with Azure OpenAI](../how-to/create-resource.md).
 - [The .NET 8.0 SDK](https://dotnet.microsoft.com/en-us/download)
 
-## Create the .NET app
+### Microsoft Entra ID prerequisites
 
-1. Create a .NET app using the `dotnet new` command:
+For the recommended keyless authentication with Microsoft Entra ID, you need to:
+- Install the [Azure CLI](/cli/azure/install-azure-cli) used for keyless authentication with Microsoft Entra ID.
+- Assign the `Cognitive Services User` role to your user account. You can assign roles in the Azure portal under **Access control (IAM)** > **Add role assignment**.
 
-    ```dotnetcli
-    dotnet new console -n TextToSpeech
-    ```
+## Set up
 
-1. Change into the directory of the new app:
+1. Create a new folder `to-speech-quickstart` to contain the application and open Visual Studio Code in that folder with the following command:
 
-    ```dotnetcli
-    cd OpenAISpeech
+    ```shell
+    mkdir to-speech-quickstart && cd to-speech-quickstart
     ```
 
-1. Install the [`Azure.OpenAI`](https://www.nuget.org/packages/Azure.AI.OpenAI/) client library:
-    
-    ```dotnetcli
-    dotnet add package Azure.AI.OpenAI
+1. Create a new console application with the following command:
+
+    ```shell
+    dotnet new console
     ```
 
-## Authenticate and connect to Azure OpenAI
+3. Install the [OpenAI .NET client library](https://www.nuget.org/packages/Azure.AI.OpenAI/) with the [dotnet add package](/dotnet/core/tools/dotnet-add-package) command:
 
-To make requests to your Azure OpenAI service, you need the service endpoint as well as authentication credentials via one of the following options:
+    ```console
+    dotnet add package Azure.AI.OpenAI
+    ```
 
-- [Microsoft Entra ID](/entra/fundamentals/whatis) is the recommended approach for authenticating to Azure services and is more secure than key-based alternatives. 
-- Access keys allow you to provide a secret key to connect to your resource.
+1. For the **recommended** keyless authentication with Microsoft Entra ID, install the [Azure.Identity](https://www.nuget.org/packages/Azure.Identity) package with:
 
-[!INCLUDE [Azure Key Vault](~/reusable-content/ce-skilling/azure/includes/ai-services/security/azure-key-vault.md)]
+    ```console
+    dotnet add package Azure.Identity
+    ```
 
-### Get the Azure OpenAI endpoint
+1. For the **recommended** keyless authentication with Microsoft Entra ID, sign in to Azure with the following command:
 
-The service endpoint can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively, you can find the endpoint via the **Deployments** page in Azure AI Foundry portal. An example endpoint is: `https://docs-test-001.openai.azure.com/`.
+    ```console
+    az login
+    ```
 
-:::image type="content" source="../media/quickstarts/endpoint.png" alt-text="Screenshot of the overview UI for an Azure OpenAI resource in the Azure portal with the endpoint & access keys location highlighted." lightbox="../media/quickstarts/endpoint.png":::
+## Retrieve resource information
 
-### Authenticate using Microsoft Entra ID
+[!INCLUDE [resource authentication](resource-authentication.md)]
 
-If you choose to use Microsoft Entra ID authentication, you'll need to complete the following:
+## Run the quickstart
 
-1. Add the [`Azure.Identity`](https://www.nuget.org/packages/Azure.Identity) package.
+The sample code in this quickstart uses Microsoft Entra ID for the recommended keyless authentication. If you prefer to use an API key, you can replace the `DefaultAzureCredential` object with an `AzureKeyCredential` object. 
 
-    ```dotnetcli
-    dotnet add package Azure.Identity
-    ```
+#### [Microsoft Entra ID](#tab/keyless)
 
-1. Assign the `Cognitive Services User` role to your user account. This can be done in the Azure portal on your OpenAI resource under **Access control (IAM)** > **Add role assignment**.
-1. Sign-in to Azure using Visual Studio or the Azure CLI via `az login`.
+```csharp
+AzureOpenAIClient openAIClient = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential()); 
+```
 
-### Authenticate using keys
+#### [API key](#tab/api-key)
 
-The access key value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either `KEY1` or `KEY2`. Always having two keys allows you to securely rotate and regenerate keys without causing a service disruption.
+```csharp
+AzureOpenAIClient openAIClient = new AzureOpenAIClient(new Uri(endpoint), new AzureKeyCredential(key));
+```
+---
 
-## Update the app code
+> [!NOTE]
+> You can get sample audio files, such as *wikipediaOcelot.wav*, from the [Azure AI Speech SDK repository at GitHub](https://github.com/Azure-Samples/cognitive-services-speech-sdk/tree/master/sampledata/audiofiles).
 
-1. Replace the contents of `program.cs` with the following code and update the placeholder values with your own.
+To run the quickstart, follow these steps:
 
+1. Replace the contents of `Program.cs` with the following code and update the placeholder values with your own.
+    
     ```csharp
     using Azure;
     using Azure.AI.OpenAI;
@@ -89,7 +98,7 @@ The access key value can be found in the **Keys & Endpoint** section when examin
     var speechFilePath = "YOUR_AUDIO_FILE_PATH";
     
     AzureOpenAIClient openAIClient = new AzureOpenAIClient(endpoint, credentials);
-    var audioClient = openAIClient.GetAudioClient(deploymentName);
+    AudioClient = openAIClient.GetAudioClient(deploymentName);
     
     var result = await audioClient.GenerateSpeechAsync(
                     "the quick brown chicken jumped over the lazy dogs");
@@ -105,4 +114,6 @@ The access key value can be found in the **Keys & Endpoint** section when examin
     dotnet run
     ```
 
-    The app generates an audio file at the location you specified for the `speechFilePath` variable. Play the file on your device to hear the generated audio.
+## Output
+
+The application will generate an audio file at the location you specified for the `speechFilePath` variable. Play the file on your device to hear the generated audio.

@@ -5,7 +5,7 @@ author: travisw
 ms.author: travisw
 ms.service: azure-ai-openai
 ms.topic: include
-ms.date: 01/09/2025
+ms.date: 3/11/2025
 ---
 
 [!INCLUDE [Set up required variables](./use-your-data-common-variables.md)]
@@ -66,7 +66,7 @@ foreach (ChatCitation citation in onYourDataContext?.Citations ?? [])
 > For production, use a secure way of storing and accessing your credentials like [Azure Key Vault](/azure/key-vault/general/overview). For more information about credential security, see the Azure AI services [security](../../security-features.md) article.
 
 ```cmd
-dotnet run program.cs
+dotnet run Program.cs
 ```
 
 ## Output

@@ -1,10 +1,10 @@
 ---
 services: ai-services
-author: mrbullwinkle
-ms.author: mbullwin
-ms.service: openai
+author: eric-urban
+ms.author: eur
+ms.service: azure-ai-openai
 ms.topic: include
-ms.date: 3/19/2024
+ms.date: 3/11/2025
 ---
 
 ## Prerequisites
@@ -13,73 +13,88 @@ ms.date: 3/19/2024
 - An Azure OpenAI resource with a Whisper model deployed in a [supported region](../concepts/models.md#whisper-models). For more information, see [Create a resource and deploy a model with Azure OpenAI](../how-to/create-resource.md).
 - [The .NET 8.0 SDK](https://dotnet.microsoft.com/en-us/download)
 
-## Set up
+### Microsoft Entra ID prerequisites
 
-### Retrieve key and endpoint
+For the recommended keyless authentication with Microsoft Entra ID, you need to:
+- Install the [Azure CLI](/cli/azure/install-azure-cli) used for keyless authentication with Microsoft Entra ID.
+- Assign the `Cognitive Services User` role to your user account. You can assign roles in the Azure portal under **Access control (IAM)** > **Add role assignment**.
 
-To successfully make a call against Azure OpenAI, you need an *endpoint* and a *key*.
+## Set up
 
-|Variable name | Value |
-|--------------------------|-------------|
-| `AZURE_OPENAI_ENDPOINT`               | The service endpoint can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. Alternatively, you can find the endpoint via the **Deployments** page in Azure AI Foundry portal. An example endpoint is: `https://docs-test-001.openai.azure.com/`.|
-| `AZURE_OPENAI_API_KEY` | This value can be found in the **Keys & Endpoint** section when examining your resource from the Azure portal. You can use either `KEY1` or `KEY2`.|
+1. Create a new folder `whisper-quickstart` to contain the application and open Visual Studio Code in that folder with the following command:
 
-Go to your resource in the Azure portal. The **Endpoint and Keys** can be found in the **Resource Management** section. Copy your endpoint and access key as you'll need both for authenticating your API calls. You can use either `KEY1` or `KEY2`. Always having two keys allows you to securely rotate and regenerate keys without causing a service disruption.
+    ```shell
+    mkdir whisper-quickstart && cd whisper-quickstart
+    ```
 
-:::image type="content" source="../media/quickstarts/endpoint.png" alt-text="Screenshot of the overview UI for an Azure OpenAI resource in the Azure portal with the endpoint & access keys location circled in red." lightbox="../media/quickstarts/endpoint.png":::
+1. Create a new console application with the following command:
 
-## Create the .NET app
+    ```shell
+    dotnet new console
+    ```
 
-1. Create a .NET app using the `dotnet new` command:
+3. Install the [OpenAI .NET client library](https://www.nuget.org/packages/Azure.AI.OpenAI/) with the [dotnet add package](/dotnet/core/tools/dotnet-add-package) command:
 
-    ```dotnetcli
-    dotnet new console -n OpenAIWhisper
+    ```console
+    dotnet add package Azure.AI.OpenAI
     ```
 
-1. Change into the directory of the new app:
+1. For the **recommended** keyless authentication with Microsoft Entra ID, install the [Azure.Identity](https://www.nuget.org/packages/Azure.Identity) package with:
 
-    ```dotnetcli
-    cd OpenAIWhisper
+    ```console
+    dotnet add package Azure.Identity
     ```
 
-1. Install the [`Azure.OpenAI`](https://www.nuget.org/packages/Azure.AI.OpenAI/) client library:
+1. For the **recommended** keyless authentication with Microsoft Entra ID, sign in to Azure with the following command:
 
-    ```dotnetcli
-    dotnet add package Azure.AI.OpenAI
+    ```console
+    az login
     ```
 
-## Passwordless authentication is recommended
+## Retrieve resource information
 
-Passwordless authentication is more secure than key-based alternatives and is the recommended approach for connecting to Azure services. If you choose to use Passwordless authentication, you'll need to complete the following:
+[!INCLUDE [resource authentication](resource-authentication.md)]
 
-1. Add the [`Azure.Identity`](https://www.nuget.org/packages/Azure.Identity) package.
+## Run the quickstart
 
-    ```dotnetcli
-    dotnet add package Azure.Identity
-    ```
+The sample code in this quickstart uses Microsoft Entra ID for the recommended keyless authentication. If you prefer to use an API key, you can replace the `DefaultAzureCredential` object with an `AzureKeyCredential` object. 
+
+#### [Microsoft Entra ID](#tab/keyless)
+
+```csharp
+AzureOpenAIClient openAIClient = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential()); 
+```
 
-1. Assign the `Cognitive Services User` role to your user account. This can be done in the Azure portal on your OpenAI resource under **Access control (IAM)** > **Add role assignment**.
-1. Sign-in to Azure using Visual Studio or the Azure CLI via `az login`.
+#### [API key](#tab/api-key)
 
-## Update the app code
+```csharp
+AzureOpenAIClient openAIClient = new AzureOpenAIClient(new Uri(endpoint), new AzureKeyCredential(key));
+```
+---
+
+> [!NOTE]
+> You can get sample audio files, such as *wikipediaOcelot.wav*, from the [Azure AI Speech SDK repository at GitHub](https://github.com/Azure-Samples/cognitive-services-speech-sdk/tree/master/sampledata/audiofiles).
 
-1. Replace the contents of `program.cs` with the following code and update the placeholder values with your own.
+To run the quickstart, follow these steps:
 
-    > [!NOTE]
-    > You can get sample audio files, such as *wikipediaOcelot.wav*, from the [Azure AI Speech SDK repository at GitHub](https://github.com/Azure-Samples/cognitive-services-speech-sdk/tree/master/sampledata/audiofiles).
+1. Replace the contents of `Program.cs` with the following code and update the placeholder values with your own.
     
     ```csharp
     using Azure;
     using Azure.AI.OpenAI;
     using Azure.Identity; // Required for Passwordless auth
     
-    var endpoint = new Uri("YOUR_OPENAI_ENDPOINT");
-    var credentials = new AzureKeyCredential("YOUR_OPENAI_KEY");
-    // var credentials = new DefaultAzureCredential(); // Use this line for Passwordless auth
-    var deploymentName = "whisper"; // Default deployment name, update with your own if necessary
-    var audioFilePath = "YOUR_AUDIO_FILE_PATH";
     
-    AzureOpenAIClient openAIClient = new AzureOpenAIClient(endpoint, credentials);
+    string deploymentName = "whisper";
+    
+    string endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? "https://<your-resource-name>.openai.azure.com/";
+    string key = Environment.GetEnvironmentVariable("AZURE_OPENAI_API_KEY") ?? "<your-key>";
+    
+    // Use the recommended keyless credential instead of the AzureKeyCredential credential.
+    AzureOpenAIClient openAIClient = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential()); 
+    //AzureOpenAIClient openAIClient = new AzureOpenAIClient(new Uri(endpoint), new AzureKeyCredential(key));
+    
+    var audioFilePath = "<audio file path>"
     
     var audioClient = openAIClient.GetAudioClient(deploymentName);
     
@@ -92,19 +107,18 @@ Passwordless authentication is more secure than key-based alternatives and is th
     }
     ```
 
-[!INCLUDE [Azure Key Vault](~/reusable-content/ce-skilling/azure/includes/ai-services/security/azure-key-vault.md)]
-
 1. Run the application using the `dotnet run` command or the run button at the top of Visual Studio:
 
     ```dotnetcli
     dotnet run
     ```
 
-    If you are using the sample audio file, you should see the following text printed out in the console:
+## Output
 
-    ```text
-    The ocelot, Lepardus paradalis, is a small wild cat native to the southwestern United States, 
-    Mexico, and Central and South America. This medium-sized cat is characterized by solid 
-    black spots and streaks on its coat, round ears...
-    ```
-    
\ No newline at end of file
+If you are using the sample audio file, you should see the following text printed out in the console:
+
+```text
+The ocelot, Lepardus paradalis, is a small wild cat native to the southwestern United States, 
+Mexico, and Central and South America. This medium-sized cat is characterized by solid 
+black spots and streaks on its coat, round ears...
+```

@@ -2,7 +2,7 @@
 services: ai-services
 author: mrbullwinkle
 ms.author: mbullwin
-ms.service: openai
+ms.service: azure-ai-openai
 ms.topic: include
 ms.date: 3/19/2024
 ---

@@ -1293,7 +1293,7 @@ You use the `RealtimeRequestSession` object when you want to update the session
 | + total_tokens | integer | The total number of tokens in the Response including input and output text and audio tokens.<br><br>A property of the `usage` object. | 
 | + input_tokens | integer | The number of input tokens used in the response, including text and audio tokens.<br><br>A property of the `usage` object. |
 | + output_tokens | integer | The number of output tokens sent in the response, including text and audio tokens.<br><br>A property of the `usage` object. | 
-| + input_token_details | object | Details about the input tokens used in the response.<br><br>A property of the `usage` object.<br>br><br>See nested properties next.|
+| + input_token_details | object | Details about the input tokens used in the response.<br><br>A property of the `usage` object.<br><br>See nested properties next.|
 | + cached_tokens | integer | The number of cached tokens used in the response.<br><br>A property of the `input_token_details` object. | 
 | + text_tokens | integer | The number of text tokens used in the response.<br><br>A property of the `input_token_details` object. | 
 | + audio_tokens | integer | The number of audio tokens used in the response.<br><br>A property of the `input_token_details` object. |