Skip to main content
To connect Cursor to BetterToken, prepare an API key, enter the Base URL shown below, and choose a current Model ID from the model plaza.

​
Key settings

​
Prerequisites

​
Additional requirements

​
Install

Download and install the current version from the Cursor website. Sign in with a Cursor account that supports custom models, then continue below.
Cursor only lets users on a paid advanced tier or higher configure custom models. If your account or client version does not show custom model, API Key, or Base URL options, check your Cursor plan and client version first.
Known issue: Override OpenAI Base URL is a global setting. When enabled, it affects all API keys configured in Cursor, including Anthropic and GPT keys used by Cursor’s built-in models. Cursor’s official community has confirmed this behavior: setting a Base URL affects all API keys and models (community thread).If Cursor’s built-in Claude / GPT models stop working after you enable Override OpenAI Base URL, turn Override OpenAI Base URL off when you are not using BetterToken. Cursor currently does not support a different Base URL per model; that capability is still tracked as a feature request (feature request).

​
Manual setup

Complete this setup in the Cursor settings UI. You do not need to edit a configuration file.

​
Setup

1

Open the model settings page

In Cursor, click Settings in the lower-left corner, then go to Models. Scroll down to API Keys.
2

Enter the Base URL and API Key

In API Keys, configure the fields in this order:
  1. Enable Override OpenAI Base URL
  2. Enter https://bettertoken.ai/v1 in the Base URL field
  3. Paste your BetterToken API Key into OpenAI API Key
  4. After the URL and key are filled in, enable the OpenAI API Key toggle
Enter the key before turning on the toggle. This makes Cursor show the authentication confirmation dialog.
3

Enable the OpenAI API Key

In the confirmation dialog, click Enable OpenAI API Key.
4

Refresh the model list and enable models

Back in Models, click the refresh button on the right before selecting a model. Wait until the model list finishes refreshing.Only select models that belong to the provider supported by the configured endpoint. When using a BetterToken API key, choose a model ID from the supported provider in the model plaza, then turn on the toggle for that model.
5

Return to chat and turn off Auto

After setup, return to the Cursor chat screen and open the model picker below the input box. If Auto is enabled, turn Auto off first.
6

Select the model and start chatting

Choose the model from a supported provider you enabled, then start chatting.

​
Verify the connection

Send a short test prompt. If the tool returns a response without an authentication or Model ID error, the connection works. Fully restart the tool after changing its configuration.

​
Switch models

Open the model selector or change the Model field in the configuration. Use the exact Model ID from the model plaza, then restart the current session.

​
Common errors

​
Custom API and API Key errors

Before changing models or keys, compare your settings with the Cursor custom OpenAI API configuration.

​
Cursor does not show Custom API, API Key, or Base URL fields

Check your Cursor plan and client version. Custom models are available only in supported paid tiers. After updating Cursor, open Settings → Models again.

​
The API Key cannot be enabled or verified

Enter the Base URL https://bettertoken.ai/v1 and the API Key before turning on the OpenAI API Key toggle. Do not append /chat/completions to the Base URL, and do not use a Claude provider key.

​
The model is missing after refresh

Confirm that the selected Model ID comes from the supported provider, wait for refresh to finish, and enable only a model from that provider. The model plaza always lists current IDs.

​
Cursor built-in models stop working

Override OpenAI Base URL is global. When you are not using BetterToken, turn this toggle off so Cursor can use its own Base URL again.

​
Chat selects a different model

Open the model picker and turn Auto off. Then manually select the model you enabled.

​
Advanced setup

​
Supported providers

Statuses apply to the BetterToken setup documented on this page.
  • Manual setup: enter the API Key, Base URL, and Model.
  • Not supported: no verified direct setup is currently available.

​
Technical details

This setup uses https://bettertoken.ai/v1. The tool appends the OpenAI-compatible endpoint path. Do not add /chat/completions or /responses unless a specific field explicitly requires it.

​
Notes

  • Do not use Claude provider model IDs in the Codex / OpenAI-compatible flow
  • Do not keep using hardcoded Claude model names; use a current model ID from a supported provider from the model plaza