> ## 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.

# Warp | AI Gateway

> Route the Warp Agent through the Orq.ai AI Gateway to access the full model catalog, including Claude, from a single API key.

[**Warp**](https://www.warp.dev/) is a modern terminal with a built-in AI agent. Add the **Orq.ai AI Gateway** as a custom inference endpoint to access every model in the catalog, including Anthropic Claude models, from a single API key. The **AI Gateway** is OpenAI-compatible, which is exactly what Warp's custom inference support expects.

## Prerequisites

* [**Warp**](https://www.warp.dev/) installed
* Active **Orq.ai** account
* [**Orq.ai** API key](/docs/ai-gateway/configuration/api-keys)

## Setup

Open Warp Settings, then go to **Agents** → **Warp Agent**. Under **Custom inference**, click **+ Add custom model**.

<Frame caption="Custom inference settings in the Warp Agent panel">
  <img src="https://mintcdn.com/orqai/MvnfKIthan8NqtE1/images/gateway-warp-settings.png?fit=max&auto=format&n=MvnfKIthan8NqtE1&q=85&s=e9be1b7f7c1eb996de74a5bd256349ab" alt="Warp Agent settings showing the Custom inference section with the Add custom model button" width="2008" height="1282" data-path="images/gateway-warp-settings.png" />
</Frame>

In the **Edit custom endpoint** dialog, fill the fields:

| Field             | Value                          |
| ----------------- | ------------------------------ |
| **Endpoint name** | `orq`                          |
| **Endpoint URL**  | `https://api.orq.ai/v3/router` |
| **API key**       | `<ORQ_API_KEY>`                |
| **Model name**    | `anthropic/claude-sonnet-4-6`  |

Replace `<ORQ_API_KEY>` with an [API key](/docs/ai-gateway/configuration/api-keys).

Click **+ Add model** for each additional model, set an optional **Model alias** for the picker, then **Save**.

<Frame caption="Adding the Orq.ai AI Gateway as a custom endpoint in Warp">
  <img src="https://mintcdn.com/orqai/MvnfKIthan8NqtE1/images/gateway-warp-endpoint.png?fit=max&auto=format&n=MvnfKIthan8NqtE1&q=85&s=e5c3aade48f5ea80651ed10add1506d3" alt="Warp Edit custom endpoint dialog with the Orq endpoint name, the v3 router URL, and two models added" width="1080" height="1108" data-path="images/gateway-warp-endpoint.png" />
</Frame>

Select the model from Warp's model picker and start using the Warp Agent.

<Warning>
  Always use the `provider/model_id` format for model names (e.g. `anthropic/claude-sonnet-4-6`, not `claude-sonnet-4-6`). Bare IDs return a `400 invalid model format` error.
</Warning>

## Troubleshooting

<AccordionGroup>
  <Accordion title="400 invalid model format">
    The model name is missing the provider prefix. Change `claude-sonnet-4-6` to `anthropic/claude-sonnet-4-6`, `gpt-4o` to `openai/gpt-4o`, and so on.
  </Accordion>

  <Accordion title="Requests not appearing in Orq.ai Traces">
    Verify the **Endpoint URL** is set to `https://api.orq.ai/v3/router`. Requests sent to a provider's own endpoint bypass the **AI Gateway** and produce no **Traces**.
  </Accordion>
</AccordionGroup>

## Verification

Send a message in the Warp Agent. The response appears in the terminal and the request appears in [**Orq.ai** Traces](/docs/ai-gateway/traces) with the model identifier `anthropic/claude-sonnet-4-6` (or whichever model was selected).