@@ -6,7 +6,7 @@ author: mrbullwinkle
 ms.author: mbullwin
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 09/20/2024
+ms.date: 03/27/2025
 ms.custom: template-concept, ignite-2024
 manager: nitinme
 ---
@@ -29,7 +29,7 @@ There are several components to abuse monitoring:
 
 ## Modified abuse monitoring 
 
-Some customers may want to use the Azure OpenAI Service for a use case that involves the processing of highly sensitive or highly confidential data, or otherwise may conclude that they don't want or don't have the right to permit Microsoft to store and conduct human review on their prompts and completions for abuse detection. To address these concerns, Microsoft allows customers who meet additional Limited Access eligibility criteria to apply to modify abuse monitoring by completing [this ](https://customervoice.microsoft.com/Pages/ResponsePage.aspx?id=v4j5cvGGr0GRqy180BHbR7en2Ais5pxKtso_Pz4b1_xUOE9MUTFMUlpBNk5IQlZWWkcyUEpWWEhGOCQlQCN0PWcu)form. Learn more about applying for modified abuse monitoring at [Limited access to Azure OpenAI Service](/legal/cognitive-services/openai/limited-access?context=%2Fazure%2Fai-services%2Fopenai%2Fcontext%2Fcontext), and about the impact of modified abuse monitoring on data processing at [Data, privacy, and security for Azure OpenAI Service](/legal/cognitive-services/openai/data-privacy?context=%2Fazure%2Fai-services%2Fopenai%2Fcontext%2Fcontext&tabs=azure-portal).    
+Some customers may want to use the Azure OpenAI Service for a use case that involves the processing of highly sensitive or highly confidential data, or otherwise may conclude that they don't want or don't have the right to permit Microsoft to store and conduct human review on their prompts and completions for abuse detection. To address these concerns, Microsoft allows customers who meet additional Limited Access eligibility criteria to apply to modify abuse monitoring by completing [this](https://customervoice.microsoft.com/Pages/ResponsePage.aspx?id=v4j5cvGGr0GRqy180BHbR7en2Ais5pxKtso_Pz4b1_xUOE9MUTFMUlpBNk5IQlZWWkcyUEpWWEhGOCQlQCN0PWcu)form. Learn more about applying for modified abuse monitoring at [Limited access to Azure OpenAI Service](/legal/cognitive-services/openai/limited-access?context=%2Fazure%2Fai-services%2Fopenai%2Fcontext%2Fcontext), and about the impact of modified abuse monitoring on data processing at [Data, privacy, and security for Azure OpenAI Service](/legal/cognitive-services/openai/data-privacy?context=%2Fazure%2Fai-services%2Fopenai%2Fcontext%2Fcontext&tabs=azure-portal).    
 
 > [!NOTE]
 > When abuse monitoring is modified and human review is not performed, detection of potential abuse may be less accurate. Customers are notified of potential abuse detection as described above, and should be prepared to respond to such notification to avoid service interruption if possible.  

@@ -1,12 +1,12 @@
 ---
 title: Design system messages with Azure OpenAI
 titleSuffix: Azure OpenAI Service
-description: Learn about system message design with GPT-3, GPT-35-Turbo, and GPT-4 models.
+description: Learn about system message design
 author: mrbullwinkle
 ms.author: mbullwin 
 ms.service: azure-ai-openai
 ms.topic: conceptual 
-ms.date: 09/05/2024
+ms.date: 03/26/2025
 manager: nitinme
 keywords: ChatGPT, GPT-4, meta prompts, chain of thought
 ---
@@ -17,9 +17,9 @@ This guide will walk you through some techniques in system message design.
 
 
 
-## What is a system message? 
+## What is a system message?
 
-A system message is a feature-specific set of instructions or contextual frameworks given to a generative AI model (e.g. GPT4-o, GPT3.5 Turbo, etc.) to direct and improve the quality and safety of a model’s output. This is particularly helpful in situations that need certain degrees of formality, technical language, or industry-specific terms.  
+A system message is a feature-specific set of instructions or contextual frameworks given to a generative AI model (e.g. GPT-4o, GPT-3.5 Turbo, etc.) to direct and improve the quality and safety of a model’s output. This is particularly helpful in situations that need certain degrees of formality, technical language, or industry-specific terms.  
 
 
 There is no prescribed length. A system message can be one short sentence:  

@@ -3,7 +3,7 @@ title: Azure OpenAI Service getting started with customizing a large language mo
 titleSuffix: Azure OpenAI Service
 description: Learn more about the concepts behind customizing an LLM with Azure OpenAI.
 ms.topic: conceptual
-ms.date: 09/20/2024
+ms.date: 03/27/2025
 ms.service: azure-ai-openai
 manager: nitinme
 author: mrbullwinkle

@@ -4,7 +4,7 @@ description: Learn more about what you should take into consideration before fin
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: conceptual 
-ms.date: 08/29/2024
+ms.date: 03/26/2025
 author: mrbullwinkle
 ms.author: mbullwin
 recommendations: false

@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI
 description: Learn how to use prompt engineering to optimize your work with Azure OpenAI Service.
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 08/29/2024
+ms.date: 03/26/2025
 ms.custom: references_regions, build-2023, build-2023-dataai
 manager: nitinme
 author: mrbullwinkle
@@ -14,7 +14,7 @@ recommendations: false
 
 # Prompt engineering techniques
 
-GPT-3, GPT-3.5, GPT-4, and GPT-4o models from OpenAI are prompt-based. With prompt-based models, the user interacts with the model by entering a text prompt, to which the model responds with a text completion. This completion is the model’s continuation of the input text.
+GPT-3, GPT-3.5, GPT-4, and GPT-4o models from OpenAI are prompt-based. With prompt-based models, the user interacts with the model by entering a text prompt, to which the model responds with a text completion. This completion is the model’s continuation of the input text. These techniques are note recommended for o-series models.
 
 While these models are extremely powerful, their behavior is also very sensitive to the prompt. This makes prompt construction an important skill to develop.
 

@@ -7,7 +7,7 @@ ms.service: azure-ai-openai
 ms.custom:
   - ignite-2024
 ms.topic: how-to
-ms.date: 03/10/2025
+ms.date: 03/26/2025
 author: aahill
 ms.author: aahi
 recommendations: false
@@ -120,7 +120,7 @@ In addition to the updates for the hourly payment model, in December 2024 new [A
 |gpt-4| 0613, 1106-Preview, 0125-Preview|
 |gpt-4-turbo| 2024-04-09|
 |gpt-4-32k| 0613|
-|gpt-4o| 2042-05-13, 2024-08-06|
+|gpt-4o| 2024-05-13, 2024-08-06|
 |gpt-4o-mini| 2024-07-18|
 
 

@@ -3,7 +3,7 @@ title: Azure OpenAI Service provisioned throughput
 description: Learn about provisioned throughput and Azure OpenAI.
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 08/07/2024
+ms.date: 03/26/2025
 manager: nitinme
 author: mrbullwinkle #ChrisHMSFT
 ms.author: mbullwin #chrhoder

@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI Service
 description: Learn about how red teaming and adversarial testing are an essential practice in the responsible development of systems and features using large language models (LLMs)
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 11/30/2024
+ms.date: 03/27/2025
 manager: nitinme
 author: mrbullwinkle
 ms.author: mbullwin

@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI Service
 description: Learn about how to construct system messages also know as metaprompts to guide an AI system's behavior.
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 09/20/2024
+ms.date: 03/27/2025
 ms.custom:
   - ignite-2023
 manager: nitinme

@@ -5,7 +5,7 @@ description: Learn more about how the Azure OpenAI embeddings API uses cosine si
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: tutorial
-ms.date: 10/6/2024
+ms.date: 03/27/2025
 author: mrbullwinkle
 ms.author: mbullwin
 recommendations: false

@@ -6,7 +6,7 @@ author: mrbullwinkle
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 12/02/2024
+ms.date: 03/27/2025
 ms.author: mbullwin
 ---
 

@@ -7,7 +7,7 @@ metadata:
   manager: nitinme
   ms.service: azure-ai-openai
   ms.topic: faq
-  ms.date: 08/13/2024
+  ms.date: 03/27/2025
   ms.author: mbullwin
   author: mrbullwinkle
 title: Azure OpenAI Service frequently asked questions

@@ -5,7 +5,7 @@ description: Considerations for implementing Business Continuity and Disaster Re
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: how-to
-ms.date: 12/03/2024
+ms.date: 03/27/2025
 author: mrbullwinkle    
 ms.author: mbullwin
 recommendations: false

@@ -6,15 +6,15 @@ author: mrbullwinkle #dereklegenzoff
 ms.author: mbullwin #delegenz
 ms.service: azure-ai-openai
 ms.topic: how-to
-ms.date: 12/02/2024
+ms.date: 03/27/2025
 manager: nitinme
 keywords: ChatGPT
 ---
 
 # Chat Markup Language ChatML (Preview)
 
 > [!IMPORTANT]
-> Using GPT-3.5-Turbo models with the completion endpoint as described in this article remains in preview and is only possible with `gpt-35-turbo` version (0301) which is [slated for retirement as early as August 1, 2024](../concepts/model-retirements.md#current-models). We strongly recommend using the [GA Chat Completion API/endpoint](./chatgpt.md). The Chat Completion API is the recommended method of interacting with the GPT-3.5-Turbo models. The Chat Completion API is also the only way to access the GPT-4 models.
+> Using GPT-3.5-Turbo models with the completion endpoint as described in this article remains in preview and is only possible with `gpt-35-turbo` version (0301) which was [retired for standard deployment in February 2025](../concepts/model-retirements.md#current-models). We strongly recommend using the [GA Chat Completion API/endpoint](./chatgpt.md) or the [Responses API](./responses.md). The Chat Completion API is the recommended method of interacting with the GPT-3.5-Turbo models. The Chat Completion API is also the only way to access the GPT-4 models.
 
 The following code snippet shows the most basic way to use the GPT-3.5-Turbo models with ChatML. If this is your first time using these models programmatically we recommend starting with our [GPT-35-Turbo & GPT-4 Quickstart](../chatgpt-quickstart.md).
 

@@ -1,18 +1,18 @@
 ---
-title: Work with the GPT-35-Turbo and GPT-4 models 
+title: Work with chat completion models
 titleSuffix: Azure OpenAI Service
-description: Learn about the options for how to use the GPT-35-Turbo and GPT-4 models.
+description: Learn about the options for how to use models with the chat completions API
 author: mrbullwinkle #dereklegenzoff
 ms.author: mbullwin #delegenz
 ms.service: azure-ai-openai
 ms.custom: build-2023, build-2023-dataai, devx-track-python
 ms.topic: how-to
-ms.date: 09/05/2024
+ms.date: 03/26/2025
 manager: nitinme
 keywords: ChatGPT
 ---
 
-# Work with the GPT-3.5-Turbo, GPT-4 models, and GPT-4o models
+# Work with chat completions models
 
 GPT-3.5-Turbo, GPT-4, and GPT-4o series models are language models that are optimized for conversational interfaces. The models behave differently than the older GPT-3 models. Previous models were text-in and text-out, which means they accepted a prompt string and returned a completion to append to the prompt. However, the latest models are conversation-in and message-out. The models expect input formatted in a specific chat-like transcript format. They return a completion that represents a model-written message in the chat. This format was designed specifically for multi-turn conversations, but it can also work well for nonchat scenarios.
 

@@ -5,7 +5,7 @@ description: Learn how to generate or manipulate text, including code by using t
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: how-to
-ms.date: 08/29/2024
+ms.date: 03/26/2025
 author: mrbullwinkle
 ms.author: mbullwin
 recommendations: false
@@ -17,7 +17,7 @@ recommendations: false
 Azure OpenAI Service provides a **completion endpoint** that can be used for a wide variety of tasks. The endpoint supplies a simple yet powerful text-in, text-out interface to any [Azure OpenAI model](../concepts/models.md). To trigger the completion, you input some text as a prompt. The model generates the completion and attempts to match your context or pattern. Suppose you provide the prompt "As Descartes said, I think, therefore" to the API. For this prompt, Azure OpenAI returns the completion endpoint " I am" with high probability.
 
 > [!IMPORTANT]
-> Unless you have a specific use case that requires the completions endpoint, we recommend instead using the [chat completions endpoint](./chatgpt.md) which allows you to take advantage of the latest models like GPT-4o, GPT-4o mini, and GPT-4 Turbo. 
+> Unless you have a specific use case that requires the completions endpoint, we recommend instead using the [responses API](./responses.md) of [chat completions endpoint](./chatgpt.md) which allows you to take advantage of the latest models like GPT-4o, GPT-4o mini, and GPT-4 Turbo. 
 
 The best way to start exploring completions is through the playground in [Azure AI Foundry](https://ai.azure.com). It's a simple text box where you enter a prompt to generate a completion. You can start with a simple prompt like this one:
 
@@ -36,7 +36,7 @@ The completion results that you see can differ because the Azure OpenAI API prod
 The simple text-in, text-out interface means you can "program" the Azure OpenAI model by providing instructions or just a few examples of what you'd like it to do. The output success generally depends on the complexity of the task and quality of your prompt. A general rule is to think about how you would write a word problem for a pre-teenage student to solve. A well-written prompt provides enough information for the model to know what you want and how it should respond.
 
 > [!NOTE]
-> The model training data can be different for each model type. The [latest model's training data currently extends through September 2021 only](/azure/ai-services/openai/concepts/models). Depending on your prompt, the model might not have knowledge of related current events.
+> The model training data can be different for each model type. Depending on your prompt, the model might not have knowledge of related current events.
 
 ## Design prompts
 

@@ -7,7 +7,7 @@ ms.author: mbullwin
 ms.service: azure-ai-openai
 ms.custom: devx-track-dotnet
 ms.topic: how-to
-ms.date: 11/19/2024
+ms.date: 03/27/2025
 manager: nitinme
 ---
 
@@ -25,7 +25,7 @@ Stable releases of `Azure.AI.OpenAI` are associated with a corresponding stable
 dotnet add package Azure.AI.OpenAI
 ```
 
-Beta releases of `Azure.AI.OpenAI` are associated with a corresponding preview Azure OpenAI Service API version label, for example, `2024-10-01-preview`.
+Beta releases of `Azure.AI.OpenAI` are associated with a corresponding preview Azure OpenAI Service API version label, for example, `2024-03-01-preview`.
 
 ```dotnetcli
 dotnet add package Azure.AI.OpenAI --prerelease

@@ -6,22 +6,22 @@ manager: nitinme
 ms.service: azure-ai-openai
 ms.custom: devx-track-python
 ms.topic: how-to
-ms.date: 08/29/2024
+ms.date: 03/27/2025
 author: mrbullwinkle
 ms.author: mbullwin
 recommendations: false
 ---
 # Learn how to generate embeddings with Azure OpenAI
 
-An embedding is a special format of data representation that can be easily utilized by machine learning models and algorithms. The embedding is an information dense representation of the semantic meaning of a piece of text. Each embedding is a vector of floating point numbers, such that the distance between two embeddings in the vector space is correlated with semantic similarity between two inputs in the original format. For example, if two texts are similar, then their vector representations should also be similar. Embeddings power vector similarity search in Azure Databases such as [Azure Cosmos DB for MongoDB vCore](/azure/cosmos-db/mongodb/vcore/vector-search) , [Azure SQL Database](/azure/azure-sql/database/ai-artificial-intelligence-intelligent-applications?view=azuresql&preserve-view=true#vector-search) or [Azure Database for PostgreSQL - Flexible Server](/azure/postgresql/flexible-server/how-to-use-pgvector).
+An embedding is a special format of data representation that can be easily utilized by machine learning models and algorithms. The embedding is an information dense representation of the semantic meaning of a piece of text. Each embedding is a vector of floating point numbers, such that the distance between two embeddings in the vector space is correlated with semantic similarity between two inputs in the original format. For example, if two texts are similar, then their vector representations should also be similar. Embeddings power vector similarity search in Azure Databases such as [Azure Cosmos DB for NoSQL](/azure/cosmos-db/nosql/vector-search), [Azure Cosmos DB for MongoDB vCore](/azure/cosmos-db/mongodb/vcore/vector-search), [Azure SQL Database](/azure/azure-sql/database/ai-artificial-intelligence-intelligent-applications?view=azuresql&preserve-view=true#vector-search) or [Azure Database for PostgreSQL - Flexible Server](/azure/postgresql/flexible-server/how-to-use-pgvector).
 
 ## How to get embeddings
 
 To obtain an embedding vector for a piece of text, we make a request to the embeddings endpoint as shown in the following code snippets:
 
 # [console](#tab/console)
 ```console
-curl https://YOUR_RESOURCE_NAME.openai.azure.com/openai/deployments/YOUR_DEPLOYMENT_NAME/embeddings?api-version=2024-02-01\
+curl https://YOUR_RESOURCE_NAME.openai.azure.com/openai/deployments/YOUR_DEPLOYMENT_NAME/embeddings?api-version=2024-10-21\
   -H 'Content-Type: application/json' \
   -H 'api-key: YOUR_API_KEY' \
   -d '{"input": "Sample Document goes here"}'
@@ -35,7 +35,7 @@ from openai import AzureOpenAI
 
 client = AzureOpenAI(
   api_key = os.getenv("AZURE_OPENAI_API_KEY"),  
-  api_version = "2024-06-01",
+  api_version = "2024-10-21",
   azure_endpoint =os.getenv("AZURE_OPENAI_ENDPOINT") 
 )
 
@@ -47,26 +47,6 @@ response = client.embeddings.create(
 print(response.model_dump_json(indent=2))
 ```
 
-# [OpenAI Python 0.28.1](#tab/python)
-
-[!INCLUDE [Deprecation](../includes/deprecation.md)]
-
-```python
-import openai
-
-openai.api_type = "azure"
-openai.api_key = "YOUR_API_KEY"
-openai.api_base = "https://YOUR_RESOURCE_NAME.openai.azure.com"
-openai.api_version = "2024-06-01"
-
-response = openai.Embedding.create(
-    input="Your text string goes here",
-    engine="YOUR_DEPLOYMENT_NAME"
-)
-embeddings = response['data'][0]['embedding']
-print(embeddings)
-```
-
 # [C#](#tab/csharp)
 ```csharp
 using Azure;

@@ -6,7 +6,7 @@ manager: nitinme
 ms.service: azure-ai-openai
 ms.custom: build-2023, build-2023-dataai, devx-track-python, references_regions
 ms.topic: how-to
-ms.date: 02/27/2025
+ms.date: 03/27/2025
 author: mrbullwinkle
 ms.author: mbullwin
 zone_pivot_groups: openai-fine-tuning

@@ -6,7 +6,7 @@ services: cognitive-services
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: how-to
-ms.date: 08/29/2024
+ms.date: 03/26/2025
 author: mrbullwinkle
 ms.author: mbullwin
 recommendations: false
@@ -51,7 +51,7 @@ from openai import AzureOpenAI
 client = AzureOpenAI(
   azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT"), 
   api_key=os.getenv("AZURE_OPENAI_API_KEY"),  
-  api_version="2024-03-01-preview"
+  api_version="2025-03-01-preview"
 )
 
 response = client.chat.completions.create(

@@ -5,7 +5,7 @@ description: Learn about performance and latency with Azure OpenAI
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: how-to
-ms.date: 09/20/2024
+ms.date: 03/26/2025
 author: mrbullwinkle 
 ms.author: mbullwin
 recommendations: false

@@ -7,7 +7,7 @@ ms.author: mbullwin
 ms.service: azure-ai-openai
 ms.custom: devx-track-python
 ms.topic: how-to
-ms.date: 09/26/2024
+ms.date: 03/27/2025
 manager: nitinme
 ---
 

@@ -1,7 +1,7 @@
 ---
 title: Monitor Azure OpenAI Service
 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 Service.
-ms.date: 08/20/2024
+ms.date: 03/26/2025
 ms.custom: horz-monitor, subject-monitoring
 ms.topic: conceptual
 author: mrbullwinkle

@@ -8,7 +8,7 @@ ms.custom: openai
 ms.topic: how-to
 author: mrbullwinkle
 ms.author: mbullwin
-ms.date: 09/20/2024
+ms.date: 03/26/2025
 recommendations: false
 ---
 
@@ -136,14 +136,13 @@ The inferencing code for provisioned deployments is the same a standard deployme
 
 
 ```python
-    #Note: The openai-python library support for Azure OpenAI is in preview. 
     import os
     from openai import AzureOpenAI
 
     client = AzureOpenAI(
         azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT"), 
         api_key=os.getenv("AZURE_OPENAI_API_KEY"),  
-        api_version="2024-02-01"
+        api_version="2024-10-21"
     )
 
     response = client.chat.completions.create(
@@ -203,7 +202,7 @@ from openai import AzureOpenAI
 client = AzureOpenAI(
     azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT"),
     api_key=os.getenv("AZURE_OPENAI_API_KEY"),
-    api_version="2024-02-01",
+    api_version="2024-10-21",
     max_retries=5,# default is 2
 )
 

@@ -3,7 +3,7 @@ title: Azure OpenAI Service Provisioned Throughput Units (PTU) onboarding
 description: Learn about provisioned throughput units onboarding and Azure OpenAI. 
 ms.service: azure-ai-openai
 ms.topic: conceptual 
-ms.date: 10/18/2024
+ms.date: 03/27/2025
 manager: nitinme
 author: mrbullwinkle 
 ms.author: mbullwin 

@@ -6,7 +6,7 @@ services: cognitive-services
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: how-to
-ms.date: 09/20/2024
+ms.date: 03/26/2025
 author: mrbullwinkle
 ms.author: mbullwin
 recommendations: false
@@ -50,7 +50,7 @@ from openai import AzureOpenAI
 client = AzureOpenAI(
   azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT"), 
   api_key=os.getenv("AZURE_OPENAI_API_KEY"),  
-  api_version="2024-02-01"
+  api_version="2024-10-21"
 )
 
 for i in range(3):
@@ -79,7 +79,7 @@ for i in range(3):
 $openai = @{
    api_key     = $Env:AZURE_OPENAI_API_KEY
    api_base    = $Env:AZURE_OPENAI_ENDPOINT # like the following https://YOUR_RESOURCE_NAME.openai.azure.com/
-   api_version = '2024-02-01' # may change in the future
+   api_version = '2024-10-21' # may change in the future
    name        = 'YOUR-DEPLOYMENT-NAME-HERE' # name you chose for your deployment
 }
 
@@ -145,7 +145,7 @@ from openai import AzureOpenAI
 client = AzureOpenAI(
   azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT"), 
   api_key=os.getenv("AZURE_OPENAI_API_KEY"),  
-  api_version="2024-02-01"
+  api_version="2024-10-21"
 )
 
 for i in range(3):
@@ -174,7 +174,7 @@ for i in range(3):
 $openai = @{
    api_key     = $Env:AZURE_OPENAI_API_KEY
    api_base    = $Env:AZURE_OPENAI_ENDPOINT # like the following https://YOUR_RESOURCE_NAME.openai.azure.com/
-   api_version = '2024-02-01' # may change in the future
+   api_version = '2024-10-21' # may change in the future
    name        = 'YOUR-DEPLOYMENT-NAME-HERE' # name you chose for your deployment
 }
 

@@ -7,7 +7,7 @@ metadata:
   author: mrbullwinkle
   ms.author: mbullwin
   manager: nitinme
-  ms.date: 08/29/2024
+  ms.date: 03/27/2025
   ms.service: azure-ai-openai
   ms.topic: how-to
   ms.custom:

@@ -7,7 +7,7 @@ ms.service: azure-ai-openai
 ms.custom:
   - ignite-2024
 ms.topic: how-to
-ms.date: 11/10/2024
+ms.date: 03/27/2025
 author: mrbullwinkle
 ms.author: mbullwin
 ---

@@ -5,17 +5,17 @@ description: Learn how to use the Codex models on Azure OpenAI to handle a varie
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: how-to
-ms.date: 09/20/2024
+ms.date: 03/26/2025
 author: mrbullwinkle
 ms.author: mbullwin
 ---
 
-# Codex models and Azure OpenAI Service
+# Completion models and code with Azure OpenAI Service
 
 > [!IMPORTANT]
-> This article was authored and tested against the [legacy code generation models](/azure/ai-services/openai/concepts/legacy-models). These models use the completions API, and its prompt/completion style of interaction. If you wish to test the techniques described in this article verbatim we recommend using the `gpt-35-turbo-instruct` model which allows access to the completions API. However, for code generation the chat completions API and the latest GPT-4o models will yield the best results, but the prompts would need to be converted to the conversational style specific to interacting with those models.
+> This article was authored and tested against the [legacy code generation models](/azure/ai-services/openai/concepts/legacy-models). These models use the completions API, and its prompt/completion style of interaction. If you wish to test the techniques described in this article verbatim we recommend using the `gpt-35-turbo-instruct` model which allows access to the completions API. However, for code generation the chat completions API and the latest GPT-4o and o-series models will yield the best results. To use these newer models these prompts would need to be converted to the conversational style specific to interacting with those models.
 
-The Codex model series is a descendant of our GPT-3 series that's been trained on both natural language and billions of lines of code. It's most capable in Python and proficient in over a dozen languages including C#, JavaScript, Go, Perl, PHP, Ruby, Swift, TypeScript, SQL, and even Shell.
+The Codex model series was a descendant of our GPT-3 series that's been trained on both natural language and billions of lines of code. It's most capable in Python and proficient in over a dozen languages including C#, JavaScript, Go, Perl, PHP, Ruby, Swift, TypeScript, SQL, and even Shell.
 
 You can use Codex for a variety of tasks including:
 
@@ -27,7 +27,7 @@ You can use Codex for a variety of tasks including:
 
 ## How to use completions models with code
 
-Here are a few examples of using Codex that can be tested in the [Azure AI Foundry](https://ai.azure.com) playground with a deployment of a Codex series model, such as `code-davinci-002`.
+Here are a few examples of using completion models that can be tested in the [Azure AI Foundry](https://ai.azure.com) playground with a deployment of `gpt-35-turbo-instruct`.
 
 ### Saying "Hello" (Python)
 

@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI
 description: Learn about managing model deployment life cycle, updates, & retirement.
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 08/29/2024
+ms.date: 03/26/2025
 ms.custom: references_regions, build-2023, build-2023-dataai, devx-track-azurepowershell
 manager: nitinme
 author: mrbullwinkle #ChrisHMSFT

@@ -240,7 +240,7 @@ curl https://YOUR_RESOURCE_NAME.openai.azure.com/openai/files/{output_file_id}/c
 Cancels an in-progress batch. The batch will be in status `cancelling` for up to 10 minutes, before changing to `cancelled`, where it will have partial results (if any) available in the output file.
 
 ```http
-curl https://YOUR_RESOURCE_NAME.openai.azure.com/openai/batches/{batch_id}/cancel?api-version=2024-10-21 \
+curl -X POST https://YOUR_RESOURCE_NAME.openai.azure.com/openai/batches/{batch_id}/cancel?api-version=2024-10-21 \
   -H "api-key: $AZURE_OPENAI_API_KEY" 
 ```
 

@@ -16,23 +16,19 @@ keywords: ChatGPT
 
 The following code snippet shows the most basic way to interact with models that use the Chat Completion API. If this is your first time using these models programmatically, we recommend that you start with the [chat completions quickstart](../chatgpt-quickstart.md).
 
-> [!NOTE]  
-> In the Azure OpenAI documentation, we refer to GPT-3.5-Turbo and GPT-35-Turbo interchangeably. The official name of the model on OpenAI is `gpt-3.5-turbo`. For Azure OpenAI, because of Azure-specific character constraints, the underlying model name is `gpt-35-turbo`.
-
-# [OpenAI Python 1.x](#tab/python-new)
 
 ```python
 import os
 from openai import AzureOpenAI
 
 client = AzureOpenAI(
   api_key = os.getenv("AZURE_OPENAI_API_KEY"),  
-  api_version = "2024-02-01",
+  api_version = "2024-10-21",
   azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT")
 )
 
 response = client.chat.completions.create(
-    model="gpt-35-turbo", # model = "deployment_name".
+    model="gpt-4o", # model = "deployment_name".
     messages=[
         {"role": "system", "content": "Assistant is a large language model trained by OpenAI."},
         {"role": "user", "content": "Who were the founders of Microsoft?"}
@@ -77,7 +73,7 @@ print(response.choices[0].message.content)
     }
   ],
   "created": 1698892410,
-  "model": "gpt-35-turbo",
+  "model": "gpt-4o",
   "object": "chat.completion",
   "usage": {
     "completion_tokens": 73,
@@ -111,87 +107,18 @@ print(response.choices[0].message.content)
 Microsoft was founded by Bill Gates and Paul Allen. They established the company on April 4, 1975. Bill Gates served as the CEO of Microsoft until 2000 and later as Chairman and Chief Software Architect until his retirement in 2008, while Paul Allen left the company in 1983 but remained on the board of directors until 2000.
 ```
 
-# [OpenAI Python 0.28.1](#tab/python)
-
-[!INCLUDE [Deprecation](../includes/deprecation.md)]
-
-```python
-import os
-import openai
-openai.api_type = "azure"
-openai.api_version = "2024-02-01" 
-openai.api_base = os.getenv("AZURE_OPENAI_ENDPOINT")  # Your Azure OpenAI resource's endpoint value.
-openai.api_key = os.getenv("AZURE_OPENAI_API_KEY")
-
-response = openai.ChatCompletion.create(
-    engine="gpt-35-turbo", # The deployment name you chose when you deployed the GPT-3.5-Turbo or GPT-4 model.
-    messages=[
-        {"role": "system", "content": "Assistant is a large language model trained by OpenAI."},
-        {"role": "user", "content": "Who were the founders of Microsoft?"}
-    ]
-)
-
-print(response)
-
-# To print only the response content text:
-# print(response['choices'][0]['message']['content'])
-```
-
-### Output
-
-JSON formatting added artificially for ease of reading.
-
-```json
-{
-  "choices": [
-    {
-      "finish_reason": "stop",
-      "index": 0,
-      "message": {
-        "content": "The founders of Microsoft are Bill Gates and Paul Allen. They co-founded the company in 1975.",
-        "role": "assistant"
-      }
-    }
-  ],
-  "created": 1679014551,
-  "id": "chatcmpl-6usfn2yyjkbmESe3G4jaQR6bsScO1",
-  "model": "gpt-3.5-turbo-0301",
-  "object": "chat.completion",
-  "usage": {
-    "completion_tokens": 86,
-    "prompt_tokens": 37,
-    "total_tokens": 123
-  }
-}
-
-```
-
----
-
-> [!NOTE]  
-> The following parameters aren't available with the new GPT-35-Turbo and GPT-4 models: `logprobs`, `best_of`, and `echo`. If you set any of these parameters, you get an error.
-
 Every response includes `finish_reason`. The possible values for `finish_reason` are:
 
 * **stop**: API returned complete model output.
 * **length**: Incomplete model output because of the `max_tokens` parameter or the token limit.
 * **content_filter**: Omitted content because of a flag from our content filters.
 * **null**: API response still in progress or incomplete.
 
-Consider setting `max_tokens` to a slightly higher value than normal, such as 300 or 500. A higher value ensures that the model doesn't stop generating text before it reaches the end of the message.
-
-## Model versioning
-
-> [!NOTE]  
-> The version `gpt-35-turbo` is equivalent to the `gpt-3.5-turbo` model from OpenAI.
-
-Unlike previous GPT-3 and GPT-3.5 models, the `gpt-35-turbo` model and the `gpt-4` and `gpt-4-32k` models will continue to be updated. When you create a [deployment](../how-to/create-resource.md#deploy-a-model) of these models, you also need to specify a model version.
-
-You can find the model retirement dates for these models on the [models](../concepts/models.md) page.
+Consider setting `max_tokens` to a slightly higher value than normal. A higher value ensures that the model doesn't stop generating text before it reaches the end of the message.
 
 ## Work with the Chat Completion API
 
-OpenAI trained the GPT-35-Turbo and GPT-4 models to accept input formatted as a conversation. The messages parameter takes an array of message objects with a conversation organized by role. When you use the Python API, a list of dictionaries is used.
+OpenAI trained chat completion models to accept input formatted as a conversation. The messages parameter takes an array of message objects with a conversation organized by role. When you use the Python API, a list of dictionaries is used.
 
 The format of a basic chat completion is:
 
@@ -232,11 +159,11 @@ To trigger a response from the model, end with a user message to indicate that i
 
 ### Message prompt examples
 
-The following section shows examples of different styles of prompts that you can use with the GPT-35-Turbo and GPT-4 models. These examples are only a starting point. You can experiment with different prompts to customize the behavior for your own use cases.
+The following section shows examples of different styles of prompts that you can use with chat completions models. These examples are only a starting point. You can experiment with different prompts to customize the behavior for your own use cases.
 
 #### Basic example
 
-If you want the GPT-35-Turbo model to behave similarly to [chat.openai.com](https://chat.openai.com/), you can use a basic system message like `Assistant is a large language model trained by OpenAI.`
+If you want you chat completions model to behave similarly to [chatgpt.com](https://chatgpt.com/), you can use a basic system message like `Assistant is a large language model trained by OpenAI.`
 
 ```
 {"role": "system", "content": "Assistant is a large language model trained by OpenAI."},
@@ -309,15 +236,13 @@ The examples so far show the basic mechanics of interacting with the Chat Comple
 
 Every time a new question is asked, a running transcript of the conversation so far is sent along with the latest question. Because the model has no memory, you need to send an updated transcript with each new question or the model will lose the context of the previous questions and answers.
 
-# [OpenAI Python 1.x](#tab/python-new)
-
 ```python
 import os
 from openai import AzureOpenAI
 
 client = AzureOpenAI(
   api_key = os.getenv("AZURE_OPENAI_API_KEY"),  
-  api_version = "2024-02-01",
+  api_version = "2024-10-21",
   azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT")  # Your Azure OpenAI resource's endpoint value.
 )
 
@@ -328,48 +253,21 @@ while True:
     conversation.append({"role": "user", "content": user_input})
 
     response = client.chat.completions.create(
-        model="gpt-35-turbo", # model = "deployment_name".
+        model="gpt-4o", # model = "deployment_name".
         messages=conversation
     )
 
     conversation.append({"role": "assistant", "content": response.choices[0].message.content})
     print("\n" + response.choices[0].message.content + "\n")
 ```
 
-# [OpenAI Python 0.28.1](#tab/python)
-
-```python
-import os
-import openai
-openai.api_type = "azure"
-openai.api_version = "2024-02-01" 
-openai.api_base = os.getenv("AZURE_OPENAI_ENDPOINT")  # Your Azure OpenAI resource's endpoint value.
-openai.api_key = os.getenv("AZURE_OPENAI_API_KEY")
-
-conversation=[{"role": "system", "content": "You are a helpful assistant."}]
-
-while True:
-    user_input = input()      
-    conversation.append({"role": "user", "content": user_input})
-
-    response = openai.ChatCompletion.create(
-        engine="gpt-35-turbo", # The deployment name you chose when you deployed the GPT-35-turbo or GPT-4 model.
-        messages=conversation
-    )
-
-    conversation.append({"role": "assistant", "content": response["choices"][0]["message"]["content"]})
-    print("\n" + response['choices'][0]['message']['content'] + "\n")
-```
-
----
-
 When you run the preceding code, you get a blank console window. Enter your first question in the window and then select the `Enter` key. After the response is returned, you can repeat the process and keep asking questions.
 
 ## Manage conversations
 
-The previous example runs until you hit the model's token limit. With each question asked, and answer received, the `messages` list grows in size. The token limit for `gpt-35-turbo` is 4,096 tokens. The token limits for `gpt-4` and `gpt-4-32k` are 8,192 and 32,768, respectively. These limits include the token count from both the message list sent and the model response. The number of tokens in the messages list combined with the value of the `max_tokens` parameter must stay under these limits or you receive an error.
+The previous example runs until you hit the model's token limit. With each question asked, and answer received, the `messages` list grows in size. The token limit for chat completions models varies across models and versions The token limits for `gpt-4` and `gpt-4-32k` are 8,192 and 32,768, respectively. These limits include the token count from both the message list sent and the model response. The number of tokens in the messages list combined with the value of the `max_tokens` parameter must stay under these limits or you receive an error. Consult the [models page](../concepts/models.md) for each models token limits/context windows.
 
-It's your responsibility to ensure that the prompt and completion fall within the token limit. For longer conversations, you need to keep track of the token count and only send the model a prompt that falls within the limit.
+It's your responsibility to ensure that the prompt and completion fall within the token limit. For longer conversations, you need to keep track of the token count and only send the model a prompt that falls within the limit. Alternatively, with the [responses API](../how-to/responses.md) you can have the API handle truncation/management of the conversation history for you.
 
 > [!NOTE]  
 > We strongly recommend that you stay within the [documented input token limit](../concepts/models.md) for all models, even if you discover that you can exceed that limit.
@@ -378,16 +276,14 @@ The following code sample shows a simple chat loop example with a technique for
 
 The code uses tiktoken `0.5.1`. If you have an older version, run `pip install tiktoken --upgrade`.
 
-# [OpenAI Python 1.x](#tab/python-new)
-
 ```python
 import tiktoken
 import os
 from openai import AzureOpenAI
 
 client = AzureOpenAI(
   api_key = os.getenv("AZURE_OPENAI_API_KEY"),  
-  api_version = "2024-02-01",
+  api_version = "2024-10-21",
   azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT")  # Your Azure OpenAI resource's endpoint value.
 )
 
@@ -457,86 +353,6 @@ while True:
     print("\n" + response.choices[0].message.content + "\n")
 ```
 
-# [OpenAI Python 0.28.1](#tab/python)
-
-```python
-import tiktoken
-import openai
-import os
-
-openai.api_type = "azure"
-openai.api_version = "2024-02-01" 
-openai.api_base = os.getenv("AZURE_OPENAI_ENDPOINT")  # Your Azure OpenAI resource's endpoint value.
-openai.api_key = os.getenv("AZURE_OPENAI_API_KEY")
-
-system_message = {"role": "system", "content": "You are a helpful assistant."}
-max_response_tokens = 250
-token_limit = 4096
-conversation = []
-conversation.append(system_message)
-
-def num_tokens_from_messages(messages, model="gpt-3.5-turbo-0613"):
-    """Return the number of tokens used by a list of messages."""
-    try:
-        encoding = tiktoken.encoding_for_model(model)
-    except KeyError:
-        print("Warning: model not found. Using cl100k_base encoding.")
-        encoding = tiktoken.get_encoding("cl100k_base")
-    if model in {
-        "gpt-3.5-turbo-0613",
-        "gpt-3.5-turbo-16k-0613",
-        "gpt-4-0314",
-        "gpt-4-32k-0314",
-        "gpt-4-0613",
-        "gpt-4-32k-0613",
-        }:
-        tokens_per_message = 3
-        tokens_per_name = 1
-    elif model == "gpt-3.5-turbo-0301":
-        tokens_per_message = 4  # every message follows <|start|>{role/name}\n{content}<|end|>\n
-        tokens_per_name = -1  # if there's a name, the role is omitted
-    elif "gpt-3.5-turbo" in model:
-        print("Warning: gpt-3.5-turbo may update over time. Returning num tokens assuming gpt-3.5-turbo-0613.")
-        return num_tokens_from_messages(messages, model="gpt-3.5-turbo-0613")
-    elif "gpt-4" in model:
-        print("Warning: gpt-4 may update over time. Returning num tokens assuming gpt-4-0613.")
-        return num_tokens_from_messages(messages, model="gpt-4-0613")
-    else:
-        raise NotImplementedError(
-            f"""num_tokens_from_messages() is not implemented for model {model}."""
-        )
-    num_tokens = 0
-    for message in messages:
-        num_tokens += tokens_per_message
-        for key, value in message.items():
-            num_tokens += len(encoding.encode(value))
-            if key == "name":
-                num_tokens += tokens_per_name
-    num_tokens += 3  # every reply is primed with <|start|>assistant<|message|>
-    return num_tokens
-
-while True:
-    user_input = input("")     
-    conversation.append({"role": "user", "content": user_input})
-    conv_history_tokens = num_tokens_from_messages(conversation)
-
-    while conv_history_tokens + max_response_tokens >= token_limit:
-        del conversation[1] 
-        conv_history_tokens = num_tokens_from_messages(conversation)
-
-    response = openai.ChatCompletion.create(
-        engine="gpt-35-turbo", # The deployment name you chose when you deployed the GPT-35-Turbo or GPT-4 model.
-        messages=conversation,
-        temperature=0.7,
-        max_tokens=max_response_tokens,
-    )
-
-    conversation.append({"role": "assistant", "content": response['choices'][0]['message']['content']})
-    print("\n" + response['choices'][0]['message']['content'] + "\n")
-```
-
----
-
 In this example, after the token count is reached, the oldest messages in the conversation transcript are removed. For efficiency, `del` is used instead of `pop()`. We start at index 1 to always preserve the system message and only remove user or assistant messages. Over time, this method of managing the conversation can cause the conversation quality to degrade as the model gradually loses the context of the earlier portions of the conversation.
 
 An alternative approach is to limit the conversation duration to the maximum token length or a specific number of turns. After the maximum token limit is reached, the model would lose context if you were to allow the conversation to continue. You can prompt the user to begin a new conversation and clear the messages list to start a new conversation with the full token limit available.
@@ -545,8 +361,6 @@ The token counting portion of the code demonstrated previously is a simplified v
 
 ## Troubleshooting
 
-Here's a troubleshooting tip.
-
 ### Don't use ChatML syntax or special tokens with the chat completion endpoint
 
 Some customers try to use the [legacy ChatML syntax](../how-to/chat-markup-language.md) with the chat completion endpoints and newer models. ChatML was a preview capability that only worked with the legacy completions endpoint with the `gpt-35-turbo` version 0301 model. This model is [slated for retirement](../concepts/model-retirements.md). If you attempt to use ChatML syntax with newer models and the chat completion endpoint, it can result in errors and unexpected model response behavior. We don't recommend this use. This same issue can occur when using common special tokens.
@@ -564,5 +378,5 @@ Some customers try to use the [legacy ChatML syntax](../how-to/chat-markup-langu
 ## Next steps
 
 * [Learn more about Azure OpenAI](../overview.md).
-* Get started with the GPT-35-Turbo model with [the GPT-35-Turbo quickstart](../chatgpt-quickstart.md).
+* Get started with chat completions models with [the chat completion quickstart](../chatgpt-quickstart.md).
 * For more examples, see the [Azure OpenAI Samples GitHub repository](https://github.com/Azure-Samples/openai).

@@ -3,7 +3,7 @@ services: cognitive-services
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: include
-ms.date: 11/06/2023
+ms.date: 03/26/2025
 author: mrbullwinkle #noabenefraim
 ms.author: mbullwin
 ---
@@ -135,9 +135,9 @@ RESOURCE_ENDPOINT = os.getenv("AZURE_OPENAI_ENDPOINT")
 openai.api_type = "azure"
 openai.api_key = API_KEY
 openai.api_base = RESOURCE_ENDPOINT
-openai.api_version = "2022-12-01"
+openai.api_version = "2024-10-21"
 
-url = openai.api_base + "/openai/deployments?api-version=2022-12-01" 
+url = openai.api_base + "/openai/deployments?api-version=2024-10-21" 
 
 r = requests.get(url, headers={"api-key": API_KEY})
 

@@ -6,7 +6,7 @@ author: mrbullwinkle
 ms.author: mbullwin 
 ms.service: azure-ai-openai
 ms.topic: include
-ms.date: 09/01/2023
+ms.date: 03/26/2025
 manager: nitinme
 keywords: ChatGPT
 

@@ -5,7 +5,7 @@ description: Azure OpenAI C# support
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: include
-ms.date: 11/18/2024
+ms.date: 03/27/2025
 ---
 
 
@@ -34,10 +34,12 @@ The [stable release](/dotnet/api/azure.ai.openai.azureopenaiclientoptions.servic
 
 The [preview release](/dotnet/api/azure.ai.openai.azureopenaiclientoptions.serviceversion?view=azure-dotnet-preview&preserve-view=true) can currently target:
 
-- `2024-06-01`
 - `2024-08-01-preview`
 - `2024-09-01-preview`
 - `2024-10-01-preview`
+- `2024-12-01-preview`
+- `2025-01-01-preview`
+- `2025-03-01-preview`
 
 ## Installation
 

@@ -5,7 +5,7 @@ description: Azure OpenAI Go support
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: include
-ms.date: 11/18/2024
+ms.date: 03/27/2025
 ---
 
 [Source code](https://github.com/Azure/azure-sdk-for-go/tree/main/sdk/ai/azopenai) | [Package (pkg.go.dev)](https://pkg.go.dev/github.com/Azure/azure-sdk-for-go/sdk/ai/azopenai) | [API reference documentation](../../reference.md) | [Package reference documentation](https://pkg.go.dev/github.com/Azure/azure-sdk-for-go/sdk/ai/azopenai)   [Samples](https://pkg.go.dev/github.com/Azure/azure-sdk-for-go/sdk/ai/azopenai#pkg-examples)
@@ -15,9 +15,9 @@ ms.date: 11/18/2024
 
 Unlike the Azure OpenAI client libraries for Python and JavaScript, the Azure OpenAI Go library is targeted to a specific Azure OpenAI API version. Having access to the latest API versions impacts feature availability.
 
-Current Azure OpenAI API version target: `2024-10-01-preview`
+Current Azure OpenAI API version target: `2025-01-01-preview`
 
-This is defined in the [**custom_client.go**](https://github.com/Azure/azure-sdk-for-go/blob/9ebef43f64796118ae206a42821d9f541a231daa/sdk/ai/azopenai/custom_client.go#L37) file.
+This is defined in the [**custom_client.go**](https://github.com/Azure/azure-sdk-for-go/blob/main/sdk/ai/azopenai/custom_client.go) file.
 
 ## Installation
 

@@ -5,7 +5,7 @@ description: Azure OpenAI Java support
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: include
-ms.date: 11/18/2024
+ms.date: 03/27/2025
 ---
 
 
@@ -19,7 +19,7 @@ Version selection is controlled by the [`OpenAIServiceVersion`](/java/api/com.az
 
 The latest Azure OpenAI preview API supported is:
 
--`2024-08-01-preview`
+-`2025-01-01-preview`
 
 The latest stable (GA) release supported is:
 
@@ -33,7 +33,7 @@ The latest stable (GA) release supported is:
 <dependency>
     <groupId>com.azure</groupId>
     <artifactId>azure-ai-openai</artifactId>
-    <version>1.0.0-beta.12</version>
+    <version>1.0.0-beta.16</version>
 </dependency>
 ```
 

@@ -5,7 +5,7 @@ description: Azure OpenAI JavaScript support
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: include
-ms.date: 02/13/2025
+ms.date: 03/27/2025
 ---
 
 [Source code](https://github.com/openai/openai-node) | [Package (npm)](https://www.npmjs.com/package/openai) | [Reference](../../reference.md) |
@@ -17,7 +17,7 @@ Feature availability in Azure OpenAI is dependent on what version of the REST AP
 
 | Latest GA API | Latest Preview API|
 |:-----|:------|
-|`2024-10-21` |`2025-01-01-preview`|
+|`2024-10-21` |`2025-03-01-preview`|
 
 ## Installation
 

@@ -5,7 +5,7 @@ description: Azure OpenAI Python support
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: include
-ms.date: 11/18/2024
+ms.date: 03/27/2024
 ---
 
 [Library source code](https://github.com/openai/openai-python?azure-portal=true) | [Package (PyPi)](https://pypi.org/project/openai?azure-portal=true) | [Reference](../../reference.md) |
@@ -19,7 +19,7 @@ Feature availability in Azure OpenAI is dependent on what version of the REST AP
 
 | Latest GA API | Latest Preview API|
 |:-----|:------|
-|`2024-10-21` |`2025-01-01-preview`|
+|`2024-10-21` |`2025-03-01-preview`|
 
 ## Installation
 
@@ -488,6 +488,10 @@ print(generate_image.model_dump_json(indent=2))
 
 ---
 
+## Responses API
+
+See the [Responses API](../../how-to/responses.md) documentation.
+
 ## Completions (legacy)
 
 ### completions.create()

@@ -6,7 +6,7 @@ author: mrbullwinkle
 ms.author: mbullwin 
 ms.service: azure-ai-openai
 ms.topic: include
-ms.date: 02/16/2024
+ms.date: 03/26/2025
 manager: nitinme
 keywords: ChatGPT
 
@@ -15,7 +15,7 @@ keywords: ChatGPT
 This guide doesn't go in-depth into the mechanics behind the message structure for Chat Completions. If you aren't familiar with interacting with Chat Completions models programmatically, we recommend reading our [how-to guide on the Chat Completion API first](../how-to/chatgpt.md).  
 
 > [!NOTE]
-> All of the examples in this section of the guide were tested against a base GPT-4 model in English. If you are reading a localized version of this article in another language, these responses represent a localized translation of the English results. To learn more about potential limitations depending on what language you are using to prompt a model, please consult our [Responsible AI transparency note](/legal/cognitive-services/openai/transparency-note?context=/azure/ai-services/openai/context/context#limitations).  
+> All of the examples in this section of the guide were tested against a base GPT-4 model in English. Some techniques may produce different results with newer models like gpt-4o, and gpt 4.5. If you are reading a localized version of this article in another language, these responses represent a localized translation of the English results. To learn more about potential limitations depending on what language you are using to prompt a model, please consult our [Responsible AI transparency note](/legal/cognitive-services/openai/transparency-note?context=/azure/ai-services/openai/context/context#limitations).  
 
 
 

@@ -6,7 +6,7 @@ author: mrbullwinkle
 ms.author: mbullwin 
 ms.service: azure-ai-openai
 ms.topic: include
-ms.date: 02/16/2024
+ms.date: 03/26/2025
 manager: nitinme
 keywords: ChatGPT
 ---

@@ -5,7 +5,7 @@ description: Walkthrough on how to get started with Azure OpenAI and make your f
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: include
-ms.date: 01/03/2024
+ms.date: 03/26/2025
 ---
 
 <a href="https://github.com/openai/openai-python" target="_blank">Library source code</a> | <a href="https://pypi.org/project/openai/" target="_blank">Package (PyPi)</a> |
@@ -22,22 +22,10 @@ ms.date: 01/03/2024
 
 Install the OpenAI Python client library with:
 
-# [OpenAI Python 1.x](#tab/python-new)
-
 ```console
 pip install openai
 ```
 
-# [OpenAI Python 0.28.1](#tab/python)
-
-[!INCLUDE [Deprecation](../includes/deprecation.md)]
-
-```console
-pip install openai==0.28.1
-```
-
----
-
 > [!NOTE]
 > This library is maintained by OpenAI. Refer to the [release history](https://github.com/openai/openai-python/releases) to track the latest updates to the library.
 
@@ -64,16 +52,21 @@ Go to your resource in the Azure portal. The **Keys and Endpoint** can be found
 
 2. Replace the contents of quickstart.py with the following code. Modify the code to add your key, endpoint, and deployment name: 
 
-# [OpenAI Python 1.x](#tab/python-new)
+# [Microsoft Entra ID](#tab/entra)
 
 ```python
 import os
 from openai import AzureOpenAI
+from azure.identity import DefaultAzureCredential, get_bearer_token_provider
+
+token_provider = get_bearer_token_provider(
+    DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
+)
     
 client = AzureOpenAI(
-    api_key=os.getenv("AZURE_OPENAI_API_KEY"),  
-    api_version="2024-02-01",
-    azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT")
+    azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT"), 
+    azure_ad_token_provider=token_provider,
+    api_version="2024-10-21"
     )
     
 deployment_name='REPLACE_WITH_YOUR_DEPLOYMENT_NAME' #This will correspond to the custom name you chose for your deployment when you deployed a model. Use a gpt-35-turbo-instruct deployment. 
@@ -85,25 +78,27 @@ response = client.completions.create(model=deployment_name, prompt=start_phrase,
 print(start_phrase+response.choices[0].text)
 ```
 
-# [OpenAI Python 0.28.1](#tab/python)
+# [API Key](#tab/key)
+
+[!INCLUDE [Azure key vault](~/reusable-content/ce-skilling/azure/includes/ai-services/security/azure-key-vault.md)]
 
 ```python
 import os
-import openai
-
-openai.api_key = os.getenv("AZURE_OPENAI_API_KEY")
-openai.api_base = os.getenv("AZURE_OPENAI_ENDPOINT") # your endpoint should look like the following https://YOUR_RESOURCE_NAME.openai.azure.com/
-openai.api_type = 'azure'
-openai.api_version = '2024-02-01' # this might change in the future
-
-deployment_name='REPLACE_WITH_YOUR_DEPLOYMENT_NAME' #This will correspond to the custom name you chose for your deployment when you deployed a model. 
-
+from openai import AzureOpenAI
+    
+client = AzureOpenAI(
+    api_key=os.getenv("AZURE_OPENAI_API_KEY"),  
+    api_version="2024-10-21",
+    azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT")
+    )
+    
+deployment_name='REPLACE_WITH_YOUR_DEPLOYMENT_NAME' #This will correspond to the custom name you chose for your deployment when you deployed a model. Use a gpt-35-turbo-instruct deployment. 
+    
 # Send a completion call to generate an answer
 print('Sending a test completion job')
 start_phrase = 'Write a tagline for an ice cream shop. '
-response = openai.Completion.create(engine=deployment_name, prompt=start_phrase, max_tokens=10)
-text = response['choices'][0]['text'].replace('\n', '').replace(' .', '.').strip()
-print(start_phrase+text)
+response = client.completions.create(model=deployment_name, prompt=start_phrase, max_tokens=10)
+print(start_phrase+response.choices[0].text)
 ```
 
 ---
@@ -128,7 +123,6 @@ Write a tagline for an ice cream shop. The coldest ice cream in town!
 
 Run the code a few more times to see what other types of responses you get as the response won't always be the same.
 
-
 ### Understanding your results
 
 Since our example of `Write a tagline for an ice cream shop.` provides little context, it's normal for the model to not always return expected results. You can adjust the maximum number of tokens if the response seems unexpected or truncated.

@@ -5,7 +5,7 @@ description: Walkthrough on how to get started with Azure OpenAI and make your f
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: include
-ms.date: 02/02/2023
+ms.date: 03/26/2025
 ---
 
 ## Prerequisites
@@ -38,14 +38,27 @@ Go to your resource in the Azure portal. The **Endpoint and Keys** can be found
 
 In a bash shell, run the following command. You will need to replace `gpt-35-turbo-instruct` with the deployment name you chose when you deployed the `gpt-35-turbo-instruct` model. Entering the model name will result in an error unless you chose a deployment name that is identical to the underlying model name.
 
+# [Microsoft Entra ID](#tab/entra)
+
 ```bash
-curl $AZURE_OPENAI_ENDPOINT/openai/deployments/gpt-35-turbo-instruct/completions?api-version=2024-02-01 \
+curl $AZURE_OPENAI_ENDPOINT/openai/deployments/gpt-35-turbo-instruct/completions?api-version=2024-10-21 \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer $AZURE_OPENAI_AUTH_TOKEN" \
+  -d "{\"prompt\": \"Once upon a time\"}"
+```
+
+# [API Key](#tab/key)
+
+```bash
+curl $AZURE_OPENAI_ENDPOINT/openai/deployments/gpt-35-turbo-instruct/completions?api-version=2024-10-21 \
   -H "Content-Type: application/json" \
   -H "api-key: $AZURE_OPENAI_API_KEY" \
   -d "{\"prompt\": \"Once upon a time\"}"
 ```
 
-The format of your first line of the command with an example endpoint would appear as follows `curl https://docs-test-001.openai.azure.com/openai/deployments/{YOUR-DEPLOYMENT_NAME_HERE}/completions?api-version=2024-02-01 \`. If you encounter an error double check to make sure that you don't have a doubling of the `/` at the separation between your endpoint and `/openai/deployments`.
+---
+
+The format of your first line of the command with an example endpoint would appear as follows `curl https://docs-test-001.openai.azure.com/openai/deployments/{YOUR-DEPLOYMENT_NAME_HERE}/completions?api-version=2024-10-21 \`. If you encounter an error double check to make sure that you don't have a doubling of the `/` at the separation between your endpoint and `/openai/deployments`.
 
 If you want to run this command in a normal Windows command prompt you would need to alter the text to remove the `\` and line breaks.
 

@@ -5,7 +5,7 @@ description: Walkthrough on how to get started with Azure OpenAI and make your f
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: include
-ms.date: 09/19/2023
+ms.date: 03/26/2025
 ---
 
 ## Prerequisites

@@ -1,17 +1,17 @@
 ### YamlMime:Landing
 
 title: Azure OpenAI Service documentation # < 60 chars
-summary: Azure OpenAI Service provides access to OpenAI's models including the GPT-4o, GPT-4o mini, GPT-4, GPT-4 Turbo with Vision, GPT-3.5-Turbo, DALLE-3 and Embeddings model series with the security and enterprise capabilities of Azure. 
+summary: Azure OpenAI Service provides access to OpenAI's models including o-series, GPT-4o, GPT-4o mini, GPT-4, GPT-4 Turbo with Vision, GPT-3.5-Turbo, DALLE-3 and Embeddings model series with the security and enterprise capabilities of Azure. 
   
 metadata:
   title: Azure OpenAI Service documentation - Quickstarts, Tutorials, API Reference - Azure AI services | Microsoft Docs
-  description: Learn how to use Azure OpenAI's powerful models including the GPT-4o, GPT-4o mini, GPT-4, GPT-4 Turbo with Vision, GPT-3.5-Turbo, DALL-E 3 and Embeddings model series
+  description: Learn how to use Azure OpenAI's powerful models including o-series, GPT-4o, GPT-4o mini, GPT-4, GPT-4 Turbo with Vision, GPT-3.5-Turbo, DALL-E 3 and Embeddings model series
   ms.service: azure-ai-openai
   ms.custom:
   ms.topic: landing-page
   author: mrbullwinkle
   ms.author: mbullwin
-  ms.date: 09/18/2024
+  ms.date: 03/27/2025
 
 # linkListType: architecture | concept | deploy | download | get-started | how-to-guide | learn | overview | quickstart | reference | tutorial | video | whats-new
 # Limits: https://review.learn.microsoft.com/help/contribute/contribute-how-to-write-landing-page?branch=main#limits
@@ -86,17 +86,17 @@ landingContent:
      linkLists:
          - linkListType: get-started
            links:
-             - text: Migrate to OpenAI Python 1.x
-               url: ./how-to/migration.md
-             - text: Manage models
-               url: ./how-to/working-with-models.md
+             - text: Responses API & computer-use-preview
+               url: ./how-to/responses.md
+             - text: Reasoning models
+               url: ./how-to/reasoning.md
              - text: OpenAI versus Azure OpenAI (Python)
                url: ./how-to/switching-endpoints.yml
              - text: Global batch
                url: ./how-to/batch.md
-             - text: Role-based access control (Azure RBAC)
-               url: ./how-to/role-based-access-control.md 
-             - text: GPT-3.5 Turbo & GPT-4
+             - text: Structured outputs
+               url: ./how-to/structured-outputs.md
+             - text: Chat completion models
                url:  ./how-to/chatgpt.md
              - text: Vision-enabled models
                url:  ./how-to/gpt-with-vision.md

@@ -8,7 +8,7 @@ ms.custom: devx-track-dotnet, devx-track-python, devx-track-extended-java, devx-
 ms.topic: quickstart
 author: mrbullwinkle
 ms.author: mbullwin
-ms.date: 09/05/2024
+ms.date: 03/26/2025
 zone_pivot_groups: openai-quickstart-new
 recommendations: false
 ---

@@ -7,7 +7,7 @@ manager: nitinme
 ms.service: azure-ai-openai
 ms.custom:
 ms.topic: conceptual
-ms.date: 11/18/2024
+ms.date: 03/27/2025
 ms.author: mbullwin
 zone_pivot_groups: openai-supported-languages
 ---

@@ -5,7 +5,7 @@ description: Learn how to use Azure OpenAI's embeddings API for document search
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: tutorial
-ms.date: 08/30/2024
+ms.date: 03/26/2025
 author: mrbullwinkle #noabenefraim
 ms.author: mbullwin
 zone_pivot_groups: "openai-embeddings"

@@ -5,7 +5,7 @@ description: Learn how to use Azure OpenAI's latest fine-tuning capabilities wit
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: tutorial
-ms.date: 09/09/2024
+ms.date: 03/26/2025
 author: mrbullwinkle
 ms.author: mbullwin
 recommendations: false