Skip to main content
Warp 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

​
Setup

Open Warp Settings, then go to Agents → Warp Agent. Under Custom inference, click + Add custom model.
Warp Agent settings showing the Custom inference section with the Add custom model button

Custom inference settings in the Warp Agent panel

In the Edit custom endpoint dialog, fill the fields: Replace <ORQ_API_KEY> with an API key. Click + Add model for each additional model, set an optional Model alias for the picker, then Save.
Warp Edit custom endpoint dialog with the Orq endpoint name, the v3 router URL, and two models added

Adding the Orq.ai AI Gateway as a custom endpoint in Warp

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

​
Troubleshooting

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.
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.

​
Verification

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