> ## Documentation Index
> Fetch the complete documentation index at: https://docs.core-ai.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Azure OpenAI Provider

> Create and configure the Azure OpenAI provider for chat completions

## Overview

The Azure OpenAI provider connects core-ai to Azure OpenAI chat deployments. It uses the Azure OpenAI v1 Chat Completions API by default through the official OpenAI SDK.

Pass Azure OpenAI deployment names to `chatModel()`. The provider sends the deployment name as the Chat Completions `model` field.

## Installation

```bash theme={null}
npm install @core-ai/azure-openai
```

## createAzureOpenAI()

Create an Azure OpenAI provider instance.

```typescript theme={null}
import { createAzureOpenAI } from '@core-ai/azure-openai';

const azure = createAzureOpenAI({
    apiKey: process.env.AZURE_OPENAI_API_KEY,
    endpoint: process.env.AZURE_OPENAI_ENDPOINT,
});
```

### Options

<ParamField path="apiKey" type="string" optional>
  Your Azure OpenAI API key.
</ParamField>

<ParamField path="endpoint" type="string" optional>
  Your Azure OpenAI resource endpoint, for example
  `https://my-resource.openai.azure.com`. You can also pass a full v1 base URL
  such as `https://my-resource.openai.azure.com/openai/v1`.
</ParamField>

<ParamField path="api" type="'v1' | 'classic'" optional>
  API surface to use. Defaults to `v1`. Set `classic` to use Azure's classic
  API surface.
</ParamField>

<ParamField path="apiVersion" type="string" optional>
  Required when `api` is `classic`. Azure OpenAI API version, for example
  `2025-04-01-preview`.
</ParamField>

<ParamField path="deployment" type="string" optional>
  Classic mode only. Default Azure OpenAI deployment for the underlying SDK
  client.
</ParamField>

<ParamField path="azureADTokenProvider" type="() => Promise<string>" optional>
  Classic mode only. Token provider for Microsoft Entra ID authentication.
</ParamField>

<ParamField path="client" type="OpenAIChatClient" optional>
  Provide your own configured Azure OpenAI chat client.
</ParamField>

### Returns

`AzureOpenAIProvider` with method `chatModel()`.

## Authentication

Use an API key with the v1 API:

```typescript theme={null}
const azure = createAzureOpenAI({
    apiKey: process.env.AZURE_OPENAI_API_KEY,
    endpoint: process.env.AZURE_OPENAI_ENDPOINT,
});
```

Use the classic API by setting `api: 'classic'` and passing an API version:

```typescript theme={null}
const azure = createAzureOpenAI({
    api: 'classic',
    apiKey: process.env.AZURE_OPENAI_API_KEY,
    endpoint: process.env.AZURE_OPENAI_ENDPOINT,
    apiVersion: '2025-04-01-preview',
});
```

Classic mode can use Microsoft Entra ID by passing a token provider:

```typescript theme={null}
import {
    DefaultAzureCredential,
    getBearerTokenProvider,
} from '@azure/identity';
import { createAzureOpenAI } from '@core-ai/azure-openai';

const credential = new DefaultAzureCredential();
const azureADTokenProvider = getBearerTokenProvider(
    credential,
    'https://cognitiveservices.azure.com/.default'
);

const azure = createAzureOpenAI({
    api: 'classic',
    azureADTokenProvider,
    endpoint: process.env.AZURE_OPENAI_ENDPOINT,
    apiVersion: '2025-04-01-preview',
});
```

## Model IDs

Use your Azure OpenAI deployment name as the model id:

```typescript theme={null}
const model = azure.chatModel('customer-support-gpt-5-mini');
```

If your deployment name is different from the base model name, pass the deployment name.

## Examples

### Basic chat

```typescript theme={null}
import { generate } from '@core-ai/core-ai';
import { createAzureOpenAI } from '@core-ai/azure-openai';

const azure = createAzureOpenAI({
    apiKey: process.env.AZURE_OPENAI_API_KEY,
    endpoint: process.env.AZURE_OPENAI_ENDPOINT,
});

const result = await generate({
    model: azure.chatModel('gpt-5-mini-deployment'),
    messages: [{ role: 'user', content: 'Hello!' }],
});

console.log(result.content);
```

### Streaming

```typescript theme={null}
import { stream } from '@core-ai/core-ai';
import { createAzureOpenAI } from '@core-ai/azure-openai';

const azure = createAzureOpenAI({
    apiKey: process.env.AZURE_OPENAI_API_KEY,
    endpoint: process.env.AZURE_OPENAI_ENDPOINT,
});

const result = await stream({
    model: azure.chatModel('gpt-5-mini-deployment'),
    messages: [{ role: 'user', content: 'Count to five.' }],
});

for await (const chunk of result.textStream) {
    process.stdout.write(chunk);
}
```

## Provider-specific options

The provider follows the OpenAI Chat Completions API. Pass options via `providerOptions.openai`:

```typescript theme={null}
await generate({
    model: azure.chatModel('gpt-5-mini-deployment'),
    messages: [{ role: 'user', content: 'Hello!' }],
    providerOptions: {
        openai: {
            seed: 42,
        },
    },
});
```

See the [OpenAI compat provider](/api/providers/openai#createopenaicompat) docs for available Chat Completions options.

<Note>
  The Azure OpenAI provider supports chat models. Use `@core-ai/openai` for
  OpenAI Responses API, embeddings, and image generation.
</Note>