Work with chat completion models

Learn how to use Azure OpenAI chat completions in Python and .NET, manage multi-turn conversations, and handle context windows and common errors.

In this article, you use Python or .NET to send chat completion requests, build a multi-turn conversation, and manage the conversation’s token budget.

Chat models are language models optimized for conversational interfaces. Unlike older text-in and text-out completion models, chat models accept a transcript of messages and return a model-generated message. This format supports multi-turn conversations and nonchat scenarios.

Use the message format described in this article instead of prompting chat models like older completion models. Otherwise, the models might produce verbose or less useful responses.

For new apps, consider building on the Responses API instead of Chat Completions. To upgrade an existing app, see Azure OpenAI To Responses.

Prerequisites

• An Azure OpenAI resource with a chat completion model deployment. To create a resource and deploy a model, see Create a resource and deploy a model with Azure OpenAI.

In the code samples, replace YOUR-RESOURCE-NAME with your Azure OpenAI resource name and YOUR-DEPLOYMENT-NAME with your model deployment name.

Related content

• Use the Responses API
• Explore Foundry Models sold by Azure
• Generate embeddings