Merge pull request #4440 from mrbullwinkle/mrb_04_30_2025_freshness_002

[Azure OpenAI] freshness update pass

Author: prmerger-automator[bot]

articles/ai-services/openai/how-to/create-resource.md

@@ -6,7 +6,7 @@ manager: nitinme
 ms.service: azure-ai-openai
 ms.custom: devx-track-azurecli, build-2023, build-2023-dataai, devx-track-azurepowershell, innovation-engine
 ms.topic: how-to
-ms.date: 01/31/2025
+ms.date: 04/30/2025
 zone_pivot_groups: openai-create-resource
 author: mrbullwinkle
 ms.author: mbullwin

articles/ai-services/openai/how-to/manage-costs.md

@@ -6,7 +6,7 @@ ms.author: mbullwin
 ms.custom: subject-cost-optimization
 ms.service: azure-ai-openai
 ms.topic: how-to
-ms.date: 01/31/2025
+ms.date: 04/30/2025
 ---
 
 
@@ -30,7 +30,7 @@ Azure OpenAI Service runs on Azure infrastructure that accrues costs when you de
 
 ### Model inference chat completions
 
-Azure OpenAI chat completions model inference is [charged per 1,000 tokens with different rates](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/) depending on model and [deployment type](./deployment-types.md).
+Azure OpenAI chat completions model inference is [charged per 1,000 tokens with different rates](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/) depending on model and [deployment type](./deployment-types.md). For most models pricing is now listed in terms of 1 million tokens.
 
 Azure OpenAI models understand and process text by breaking it down into tokens. For reference, each token is roughly four characters for typical English text.
 

articles/ai-services/openai/how-to/managed-identity.md

@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI
 description: Provides guidance on how to set managed identity with Microsoft Entra ID
 ms.service: azure-ai-openai
 ms.topic: how-to 
-ms.date: 01/31/2025
+ms.date: 04/30/2025
 author: mrbullwinkle
 ms.author: mbullwin
 recommendations: false
@@ -50,13 +50,13 @@ token_provider = get_bearer_token_provider(
 )
 
 client = AzureOpenAI(
-    api_version="2024-02-15-preview",
+    api_version="2024-04-01-preview",
     azure_endpoint="https://{your-custom-endpoint}.openai.azure.com/",
     azure_ad_token_provider=token_provider
 )
 
 response = client.chat.completions.create(
-    model="gpt-35-turbo-0125", # model = "deployment_name".
+    model="gpt-4o", # model = "deployment_name".
     messages=[
         {"role": "system", "content": "You are a helpful assistant."},
         {"role": "user", "content": "Does Azure OpenAI support customer managed keys?"},

articles/ai-services/openai/includes/chatgpt-javascript.md

@@ -7,7 +7,7 @@ ms.service: azure-ai-openai
 ms.topic: include
 author: mrbullwinkle
 ms.author: mbullwin
-ms.date: 10/22
+ms.date: 04/30/2025
 ---
 
 [Source code](https://github.com/openai/openai-node) | [Package (npm)](https://www.npmjs.com/package/openai) | [Samples](https://github.com/Azure/azure-sdk-for-js/tree/main/sdk/openai/openai/samples)

articles/ai-services/openai/includes/create-resource-cli.md

@@ -77,15 +77,15 @@ az cognitiveservices account keys list \
 
 ## Deploy a model
 
-To deploy a model, use the [az cognitiveservices account deployment create](/cli/azure/cognitiveservices/account/deployment?view=azure-cli-latest&preserve-view=true#az-cognitiveservices-account-deployment-create) command. In the following example, you deploy an instance of the `text-embedding-ada-002` model and give it the name _MyModel_. When you try the example, update the code to use your values for the resource group and resource. You don't need to change the `model-version`, `model-format` or `sku-capacity`, and `sku-name` values.
+To deploy a model, use the [az cognitiveservices account deployment create](/cli/azure/cognitiveservices/account/deployment?view=azure-cli-latest&preserve-view=true#az-cognitiveservices-account-deployment-create) command. In the following example, you deploy an instance of the `gpt-4o` model and give it the name _MyModel_. When you try the example, update the code to use your values for the resource group and resource. You don't need to change the `model-version`, `model-format` or `sku-capacity`, and `sku-name` values.
 
 ```azurecli
 az cognitiveservices account deployment create \
 --name <myResourceName> \
 --resource-group  <myResourceGroupName> \
 --deployment-name MyModel \
---model-name text-embedding-ada-002 \
---model-version "1"  \
+--model-name gpt-4o \
+--model-version "2024-11-20"  \
 --model-format OpenAI \
 --sku-capacity "1" \
 --sku-name "Standard"

articles/ai-services/openai/includes/create-resource-powershell.md

@@ -64,12 +64,12 @@ Get-AzCognitiveServicesAccountKey -Name MyOpenAIResource -ResourceGroupName OAIR
 
 ## Deploy a model
 
-To deploy a model, use the [New-AzCognitiveServicesAccountDeployment](/powershell/module/az.cognitiveservices/new-azcognitiveservicesaccountdeployment) command. In the following example, you deploy an instance of the `text-embedding-ada-002` model and give it the name _MyModel_. When you try the example, update the code to use your values for the resource group and resource. You don't need to change the `model-version`, `model-format` or `sku-capacity`, and `sku-name` values. 
+To deploy a model, use the [New-AzCognitiveServicesAccountDeployment](/powershell/module/az.cognitiveservices/new-azcognitiveservicesaccountdeployment) command. In the following example, you deploy an instance of the `gpt-4o` model and give it the name _MyModel_. When you try the example, update the code to use your values for the resource group and resource. You don't need to change the `model-version`, `model-format` or `sku-capacity`, and `sku-name` values. 
 
 ```azurepowershell-interactive
 $model = New-Object -TypeName 'Microsoft.Azure.Management.CognitiveServices.Models.DeploymentModel' -Property @{
-    Name = 'text-embedding-ada-002'
-    Version = '2'
+    Name = 'gpt-4o'
+    Version = '2024-11-20'
     Format = 'OpenAI'
 }