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

# Azure

> Set up Azure OpenAI and Azure AI Foundry as a model provider in the Orq.ai AI Gateway. Import deployments with a Base URL and API key for routing, caching, and observability.

## Setting up a Model in Azure AI Foundry

[Azure AI Foundry](https://ai.azure.com/) lets you build, configure, tune and deploy the model within their environments.

### Deployment Configuration

An Azure model is managed in Azure AI Foundry and therefore won't be controlled within the **AI Studio**. You can decide on which **strategy to use for your model** within Azure AI Foundry while building your model.

For instance, **the region** where your model will be available at is configured when creating your model.

To learn more about the model possibilities, please refer to the provider documentation, see [the Azure Deployment Documentation](https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/deployments-overview).

### Content Filtering

With your model running on Azure Cloud, the model configuration won't be available within the **AI Studio**. However its configuration will **influence the behaviour** of your [Deployment](/ai-studio/ai-engineering/deployments) when called through **Orq.ai**.

Azure offers powerful customization for content filtering, letting you configure its parameters for *Violent, Hate, Sexual, and Self-Harm* content.

<Frame caption="Within Azure AI Foundry configuration, you can define thresholds for the different types of content to protect your model and tailor its behavior to your needs.">
  <img src="https://mintcdn.com/orqai/EqUGDI2og-dnTmDI/images/docs/9424bb03492b06256bc5419850ec78f0719c9d3b3f4d29a8c157b4bd9cbb51c2-image.png?fit=max&auto=format&n=EqUGDI2og-dnTmDI&q=85&s=be53075374eb55f5c531c7da10725697" alt="Within Azure AI Foundry configuration, you can define thresholds for the different types of content to protect your model and tailor its behavior to your needs." width="3123" height="1772" data-path="images/docs/9424bb03492b06256bc5419850ec78f0719c9d3b3f4d29a8c157b4bd9cbb51c2-image.png" />
</Frame>

To learn more about Content filtering, see [the Azure AI Foundry Documentation](https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/content-filtering).

## Onboarding Models to Orq.ai

Once your models are deployed and configured on Azure, you can import them into the **AI Studio**.

### Getting the Base URL and API Key from Azure AI Foundry

Your credentials are available directly on the [Azure AI Foundry](https://ai.azure.com/) homepage once you open your project. The **API key** and both the **Project endpoint** and **Azure OpenAI endpoint** are shown at the top of the page.

**Orq.ai** accepts either endpoint as the Base URL and detects the format automatically:

* **Azure OpenAI endpoint** (`https://<resource>.openai.azure.com/openai/v1`): imports the resource's OpenAI-compatible deployments.
* **Project endpoint** (`https://<resource>.services.ai.azure.com/api/projects/<project>`): imports deployments from all publishers in the project, including Anthropic, Cohere, and xAI.

<Frame caption="API key and endpoints are shown at the top of the Azure AI Foundry project homepage.">
  <img src="https://mintcdn.com/orqai/HHjqh-MIdaNoL6vT/images/azure-foundry.png?fit=max&auto=format&n=HHjqh-MIdaNoL6vT&q=85&s=bbf504783c350cfae387383255b8ea45" alt="Azure AI Foundry homepage credentials" width="5018" height="2490" data-path="images/azure-foundry.png" />
</Frame>

### Onboarding Models

Head to the [AI Gateway](/ai-gateway/using-the-router) and choose the <kbd className="key">Model</kbd> button at the top-right of the screen, then select **Azure**.

<Frame caption="Add Model menu">
  <img src="https://mintcdn.com/orqai/6eOIIn_9kp3J28Xc/images/add-models-414.png?fit=max&auto=format&n=6eOIIn_9kp3J28Xc&q=85&s=91bbacad2095b534d6711052c722caa4" alt="Add Model menu listing OpenAI Compatible, Azure, AWS Bedrock, and Import from LiteLLM" width="390" height="359" data-path="images/add-models-414.png" />
</Frame>

Enter the **Base URL** and **API Key**, then click **Fetch deployments** to automatically import all available deployments from your Azure AI Foundry project.

<Frame caption="Enter your Base URL and API Key, then fetch all available deployments at once.">
  <img src="https://mintcdn.com/orqai/HHjqh-MIdaNoL6vT/images/azure-configure.png?fit=max&auto=format&n=HHjqh-MIdaNoL6vT&q=85&s=6ba78447dcca57d3d542837d9128c1e4" alt="Azure Configure" width="1005" height="868" data-path="images/azure-configure.png" />
</Frame>

Once added, the model will be visible in the **AI Gateway**. Once the model is **Enabled** it will be available in [Playground](/ai-studio/prompts/playgrounds), [Experiment](/ai-studio/optimize/experiments), [Deployment](/ai-studio/ai-engineering/deployments), and [Agent](/ai-studio/ai-engineering/build-agents) to be used.

***