> ## 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.

# Bring Your Own Model

> Connect fine-tuned, self-hosted, and privately deployed models from OpenAI-compatible endpoints, Azure AI Foundry, AWS Bedrock, or LiteLLM to the AI Gateway.

Use private models alongside public models through the same AI Gateway endpoint. Private models are useful when you have fine-tuned models, dedicated deployments, or self-hosted inference that should remain under your infrastructure and provider contracts.

## Supported private model sources

<CardGroup cols={2}>
  <Card title="OpenAI Compatible" icon="openai" href="/ai-studio/integrations/providers/open-ai-like">
    Add models from any endpoint that implements the OpenAI API, including self-hosted and private deployments.
  </Card>

  <Card title="Azure AI Foundry" icon="microsoft" href="/ai-studio/integrations/providers/azure">
    Import OpenAI-compatible and publisher model deployments from an Azure AI Foundry project.
  </Card>

  <Card title="AWS Bedrock" icon="aws" href="/ai-studio/integrations/providers/aws-bedrock">
    Add models using Amazon Bedrock inference profiles.
  </Card>

  <Card title="LiteLLM" icon="server" href="/ai-studio/integrations/providers/litellm">
    Import self-hosted or custom models exposed through your LiteLLM instance.
  </Card>
</CardGroup>

## Add a private model

<Steps>
  <Step title="Open Models">
    In the AI Gateway sidebar, open **Models** and select <Icon icon="circle-plus" /> **Model**.
  </Step>

  <Step title="Connect the private provider">
    Select OpenAI Compatible, Azure, AWS Bedrock, or Import from LiteLLM, then follow the prompts for that source.
  </Step>

  <Step title="Import and enable models">
    Import or add the models to expose, then enable each model that should be available through the AI Gateway.
  </Step>

  <Step title="Route requests">
    Reference an imported model as `<workspace>@<provider>/<model>`.

    ```text theme={"theme":{"light":"github-light","dark":"github-dark"}}
    corp@azure/gpt-5.6-sol
    ```
  </Step>
</Steps>

Enabled private models are available for requests through [routing rules](/ai-gateway/configuration/routing-rules).

<Card title="Manage all models" icon="sliders" href="/ai-gateway/using-the-router">
  Enable models, filter by capability and region, and control model access by project.
</Card>

### OpenAI Compatible

Choose this source for any endpoint that implements the OpenAI API, including self-hosted inference servers and private gateways.

<Frame caption="OpenAI Compatible configuration form">
  <img src="https://mintcdn.com/orqai/ndgny3YfsOM4IgFq/images/openai-compatible-configuration.png?fit=max&auto=format&n=ndgny3YfsOM4IgFq&q=85&s=a88f2c20ca5c9660e86043e29f24be68" alt="OpenAI Compatible configuration form showing Connection fields for Type, Base URL, Model ID and API Key, General fields for model name, region, description, token limits and per-token prices, and Capabilities toggles for function calling, vision, structured output and reasoning" width="810" height="1380" data-path="images/openai-compatible-configuration.png" />
</Frame>

For the configuration fields, see [OpenAI-compatible models](/ai-studio/integrations/providers/open-ai-like).