Agent Tools

Cursor

Connect Cursor to Yolo Router and use a selected model for chat and coding assistance.

iBefore you start
  • Cursor is installed and can open your project.
  • A working Yolo Router endpoint, for example https://api.yolorouter.com.
  • A Yolo Router API Key generated from the console.
  • The model ID you want to use, for example deepseek-v4-pro. It must exactly match the model ID in the Yolo Router console.

Cursor custom API keys mainly apply to standard chat models. Features that rely on Cursor-specific models, such as Tab Completion and some Agent/Apply behavior, may continue to use Cursor built-in models or may not support custom keys.

Setup

Verify Yolo Router first

Before configuring Cursor, verify that the endpoint, API Key, and model ID work.

export YOLOROUTER_API_KEY="sk-yolo-..."

curl https://api.yolorouter.com/v1/models \
  -H "Authorization: Bearer $YOLOROUTER_API_KEY"
$env:YOLOROUTER_API_KEY = "sk-yolo-..."

curl.exe https://api.yolorouter.com/v1/models `
  -H "Authorization: Bearer $env:YOLOROUTER_API_KEY"

If the model list is returned, confirm that the model ID you plan to use exists, for example deepseek-v4-pro.

Open Cursor model settings

In Cursor, open:

Cursor Settings > Models

Find the OpenAI API Key settings. Depending on your Cursor version, the UI may include:

  • OpenAI API Key
  • Override OpenAI Base URL
  • Add custom model or Model Names

Enter the Yolo Router API Key and Base URL

Enter your Yolo Router API Key in OpenAI API Key.

If your Cursor version provides Override OpenAI Base URL, enter:

https://api.yolorouter.com/v1

Then click Verify. After verification succeeds, Cursor will use this key and Base URL for OpenAI-compatible requests.

If your Cursor settings page does not provide Override OpenAI Base URL, that version cannot point directly to Yolo Router. Upgrade Cursor or use a client/version that supports overriding the OpenAI Base URL.

Add the model ID

Add or enable the model ID in model settings:

deepseek-v4-pro

The model name must exactly match the model ID in the Yolo Router console. Do not use a display name, alias, or value with extra spaces.

If Cursor only shows a fixed OpenAI model list and has no custom model entry, you cannot directly select a custom Yolo Router model ID from that UI.

Test in Cursor Chat

Open Cursor Chat, select the model you added, and send a simple prompt:

Introduce the model you are using in one sentence.

If Cursor returns a normal response, the integration is working. You can also check the Yolo Router console for the corresponding request log.

Troubleshooting

Verify fails

Check these first:

  • Base URL includes /v1
  • The API Key is generated from the Yolo Router console and has no extra spaces
  • Yolo Router supports the OpenAI-compatible endpoints Cursor may call, such as /v1/models and /v1/chat/completions

Model not found

Check that the model name in Cursor exactly matches the model ID in the Yolo Router console. Use /v1/models to confirm the model ID.

Override OpenAI Base URL is missing

Cursor official docs describe custom API keys, but Base URL override availability depends on the Cursor version and settings UI. If the option is not present, API Key alone cannot connect Cursor to Yolo Router.

Tab Completion does not use Yolo Router

This is a Cursor custom API key limitation. Custom keys mainly apply to standard chat models; specialized features like Tab Completion may keep using Cursor built-in models.

On this page