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

# Azure OpenAI

## Guide

1. **Navigate to Azure Portal Resources**
   Go to the [**Azure Portal**](https://portal.azure.com/) and navigate to the Azure OpenAI Service.
2. **Create an Azure OpenAI Deployment**
   Click **Create** and complete the required fields in each section. Default values are generally sufficient. Note that the deployment may take a few minutes to finish.
3. **Create a Model Deployment**
   * Go to the [**Azure OpenAI Service**](https://oai.azure.com/) and select your new AI resource.
   * Navigate to the **Model Catalog** tab and select the model you want to use with Onyx. Click **Use this model** → **Deploy to selected resource**.
4. **Save Your Deployment Details and Credentials**
   On your deployed model page, save the **Target URI** and **API Key**. Your Target URI contains the API Base, API Version, and Deployment Name needed to configure the provider in ASSIST AI.

<Warning>
  If you encounter `I'm sorry, but I cannot assist with that request` in ASSIST AI chat responses, update the model deployment Content filter to **Default** instead of **DefaultV2**.
</Warning>

5. **Configure the Azure OpenAI Provider**
   Select **Azure OpenAI** from the list of available providers. Assign a Display Name to this configuration. Paste your **API Key** into the API Key field. From your Target URI, extract the **API Base**, **API Version**, and **Deployment Name**. Example:
6. ```text theme={null}
   https://assistaiazure.openai.azure.com/openai/deployments/gpt-4.1/chat/completions?api-version=2025-01-01-preview
   ```
7. **Configure Default Model and Provider Access**
   * The **Default Model** is automatically selected for new custom Agents and Chat sessions - enter the model you deployed into this field.
   * Under **Advanced Options**, you can choose whether the provider is publicly accessible to all users in ASSIST AI. If set to private, the provider's models will only be available to Admins and the User  you explicitly assign the provider to.