Cursor

Cursor is a code editor with a built-in agent. It reaches custom models by overriding the base URL of its OpenAI provider, so the AI Gateway stands in for OpenAI.

​

What you’ll need

• Cursor installed, on a paid plan.
• An access key from app.ngrok.ai.

​

Point Cursor at the gateway

Open Cursor Settings, go to Models, and expand API Keys:

1. Turn on OpenAI API Key and paste your ngrok.ai access key. The field is labeled OpenAI, but Cursor sends the key to whatever endpoint you configure below.
2. Turn on Override OpenAI Base URL and enter https://gateway.ngrok.ai/v1. Keep the /v1 suffix: Cursor appends /chat/completions to whatever you enter.
3. Select + Add model, enter a model ID from the model catalog, such as gpt-5.5, and enable it. Use provider:model to pin a provider.
4. Select Verify to confirm the gateway answers.

​

Test the connection

Pick your model in the chat model selector and send a prompt: Confirm the request in AI Gateway observability in app.ngrok.ai.

​

What the override doesn’t cover

Expect chat, not the whole editor. Three Cursor behaviors limit how far a custom model reaches:

• Tab completion always uses Cursor’s built-in models. It never reaches your endpoint.
• Agent and Edit also rely on Cursor’s own models, so Cursor may refuse them while a custom API key is set and ask you to disable the key.
• Where agent runs do work, Cursor’s tool definitions over an overridden base URL aren’t strictly OpenAI-shaped, so tool calls can fail against a self-hosted model even when plain chat succeeds.

​

Use a model you run yourself

To reach a model on your own machine, register it as a custom provider, then add its provider:model name as a model, such as ollama:llama3.2. See Use a model you run yourself for the full setup.

​

Next steps

• Restrict providers and models: Scope what an access key can call
• Configure fallback models: Try another model when the first one fails
• Observability: See which model served each request