Skip to main content
Route Cursor chat model calls through the Orq.ai AI Gateway by overriding the OpenAI base URL in Cursor Settings. Requests appear in Traces automatically.
Three limitations to know before starting:
  • Only the chat/plan panel (+L / Ctrl+L) routes through the custom endpoint. Composer, inline edit (+K / Ctrl+K), and tab completion remain on Cursor’s backend.
  • Setting a custom base URL disables Cursor’s default model list. Add models manually using provider-prefixed IDs (see Add a model below) or remove the base URL override to restore the defaults.
  • Custom API key and base URL override require Cursor Pro or higher.

Prerequisites

Setup

1

Open Cursor Settings and navigate to Models

Open Cursor Settings (+, / Ctrl+,) and select the Models tab.
2

Enter the API key

Enable the OpenAI API Key toggle and paste the Orq.ai API key in the field. Cursor sends this key to whatever base URL is configured below. It does not have to be an OpenAI key.
3

Set the base URL

In Override OpenAI Base URL, enter:
https://api.orq.ai/v3/router
If the field is not visible, expand the advanced options under the OpenAI API Key toggle.
4

Add a model

In the Model Names field, enter a provider-prefixed model ID (e.g. openai/gpt-5.4 or anthropic/claude-sonnet-4-6), then click Verify. A green checkmark confirms the model is reachable. Click Save.Repeat for each model to add.

Troubleshooting

Confirm the API key is a valid Orq.ai API key and that the model ID is enabled in AI GatewaySupported Models.
The model must use the provider-prefixed format (e.g. openai/gpt-5.4, not gpt-4o) and must be enabled in AI GatewaySupported Models.
Confirm the base URL is set to https://api.orq.ai/v3/router and the request is sent from the chat panel (+L / Ctrl+L). Inline edit and tab completion bypass the custom endpoint.
Setting a custom base URL disables the default Cursor model list. Remove the base URL override in Cursor Settings → Models to restore default behavior, or add the required models manually using provider-prefixed IDs.

Verification

Send a message in the chat panel (+L / Ctrl+L). The response appears in Cursor and the trace appears in Orq.ai Traces with the model identifier (e.g. openai/gpt-5.4).