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

# Using a custom OpenAI model for Omni AI

> Use custom model identifiers with OpenAI to connect Omni to Ollama, Azure OpenAI, fine-tuned models, and more.

When using OpenAI as your [AI model provider][model-providers], you can specify custom model identifiers to use models not listed in the default model dropdowns. This is useful for:

* Using locally-hosted models through Ollama (e.g., `llama3.1:70b`)
* Using Azure OpenAI deployments with custom names
* Using newly-released models before they're added to the default list
* Using fine-tuned or specialized models

## Requirements

To follow the steps in this guide, you'll need:

* **Organization Admin** permissions in Omni
* **An OpenAI API key**

## Configuration

<Note>
  Custom models default to a 400,000 token context window.
</Note>

<Steps>
  <Step>
    In Omni, navigate to **Settings > AI > Model**.
  </Step>

  <Step>
    Select **OpenAI** as the **Provider**.
  </Step>

  <Step>
    In the **Smartest model**, **Standard model**, or **Fastest model** dropdown, select **Custom model identifier**.
  </Step>

  <Step>
    Enter your model identifier in the **Custom model** field that appears (e.g., `llama3.1:70b`, `gpt-4-turbo-2024-04-09`, or your Azure deployment name).
  </Step>

  <Step>
    If your endpoint uses a different base URL (such as for Azure OpenAI or Ollama), configure the **Base URL** field.
  </Step>

  <Step>
    Enter your OpenAI API key in the **API key** field.
  </Step>

  <Step>
    Click **Save**.
  </Step>
</Steps>

After the setup is successfully completed, Omni will use the custom model for AI features. Try asking the [Omni Agent](/ai/chat) a few questions to test the setup.

## Related

* [AI in Omni](/ai)
* [AI settings](/ai/settings)
* [Alternative model providers][model-providers]

[model-providers]: /ai/settings/model-providers