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

# Azure OpenAI

> Configure Azure OpenAI Service in EnConvo

## Overview

Azure OpenAI Service provides access to OpenAI models through Microsoft's Azure cloud platform. It offers enterprise-grade security, regional data residency, and compliance certifications, making it suitable for organizations with strict data governance requirements.

## Supported Models

Models available depend on your Azure deployment. Common options include:

| Model           | Description             | Best For              |
| --------------- | ----------------------- | --------------------- |
| **GPT-4o**      | Most capable multimodal | General use, analysis |
| **GPT-4o mini** | Fast and affordable     | Daily tasks, chat     |
| **GPT-4**       | Previous flagship       | Complex reasoning     |
| **o1 / o3**     | Reasoning models        | Logic, math, code     |

<Warning>
  You must deploy a model in your Azure portal before you can use it. Azure does not provide default model endpoints -- each model requires its own deployment.
</Warning>

## Setup

<Steps>
  <Step title="Create Azure Subscription">
    1. Go to [Azure Portal](https://portal.azure.com)
    2. Sign in or create a Microsoft Azure account
    3. Ensure you have an active Azure subscription
  </Step>

  <Step title="Create Azure OpenAI Resource">
    1. In Azure Portal, search for **Azure OpenAI**
    2. Click **Create** and fill in the resource details
    3. Select your preferred region
    4. Wait for the resource to be provisioned
  </Step>

  <Step title="Deploy a Model">
    1. Open your Azure OpenAI resource
    2. Go to **Model deployments** → **Manage Deployments**
    3. Click **Create new deployment**
    4. Select a model (e.g., gpt-4o) and give it a deployment name
    5. Note down the **deployment name** -- you will need it
  </Step>

  <Step title="Get Endpoint and API Key">
    1. In your Azure OpenAI resource, go to **Keys and Endpoint**
    2. Copy the **Endpoint** URL (e.g., `https://your-resource.openai.azure.com/`)
    3. Copy one of the **API Keys**
  </Step>

  <Step title="Configure in EnConvo">
    1. Open **Settings** → **AI Provider**
    2. Select **Azure OpenAI**
    3. Go to **Credentials** module
    4. Enter your **API Key**, **Endpoint URL**, and **Deployment Name**
  </Step>
</Steps>

## Configuration

| Setting             | Description                   | Required          |
| ------------------- | ----------------------------- | ----------------- |
| **API Key**         | Azure OpenAI API key          | Yes               |
| **Endpoint**        | Your resource endpoint URL    | Yes               |
| **Deployment Name** | Name of your model deployment | Yes               |
| **API Version**     | Azure API version             | Yes (auto-filled) |
| **Temperature**     | Creativity (0-2)              | No                |

## Validate and Use

<Steps>
  <Step title="Validate credentials">
    Click **Validate** in the Azure OpenAI credential settings. Validation requires a correct API key, resource endpoint, API version, and deployment name.
  </Step>

  <Step title="Use deployment names">
    In Azure, EnConvo calls your deployment name, not just the base model name. A deployment named `my-gpt-4o` must be entered exactly as `my-gpt-4o`.
  </Step>

  <Step title="Test each deployment">
    If you maintain multiple deployments, validate and test each one before assigning it to production workflows or agents.
  </Step>
</Steps>

<Warning>
  A 404 from Azure OpenAI usually means the endpoint, API version, or deployment name does not match the Azure resource, even when the API key is valid.
</Warning>

## Pricing

Azure OpenAI pricing mirrors OpenAI's pricing but may vary by region. Check [Azure OpenAI Pricing](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/) for details.

<Note>
  Azure OpenAI billing goes through your Azure subscription. You can set spending alerts and budgets in the Azure portal.
</Note>

## Enterprise Benefits

<CardGroup cols={2}>
  <Card title="Data Residency" icon="globe">
    Choose which Azure region hosts your data
  </Card>

  <Card title="Compliance" icon="shield-check">
    SOC 2, HIPAA, GDPR, and more
  </Card>

  <Card title="Private Networking" icon="lock">
    VNet integration, private endpoints
  </Card>

  <Card title="Managed Identity" icon="id-card">
    Azure AD authentication support
  </Card>
</CardGroup>

## Troubleshooting

<AccordionGroup>
  <Accordion title="401 Unauthorized">
    * Verify your API key is correct
    * Check that the key belongs to the correct Azure OpenAI resource
    * Ensure the resource is in an active subscription
  </Accordion>

  <Accordion title="404 Deployment not found">
    * Confirm your deployment name matches exactly (case-sensitive)
    * Verify the endpoint URL is correct
    * Check that the deployment has finished provisioning in Azure portal
  </Accordion>

  <Accordion title="Region availability">
    * Not all models are available in all Azure regions
    * Check [Azure OpenAI model availability](https://learn.microsoft.com/azure/ai-services/openai/concepts/models) for your region
    * Consider creating a resource in a different region
  </Accordion>
</AccordionGroup>