Docs

Cursor

Cursor lets you replace the address it sends its OpenAI requests to. Since Helmcode speaks that same format, changing the address and the key is enough.

Warning: the base URL override does not cover all of Cursor. Autocomplete as you type uses Cursor’s own models and will keep doing so whatever you set. And in recent versions the option has stopped being visible on every plan: if you cannot find it in your settings, you have not lost it — your plan does not include it.

Configuration

1. Open the model settings

Go to Settings, then Cursor Settings, and open the Models section.

2. Paste your key

In the OpenAI keys section, put your Helmcode key, the one that starts with sk-.

3. Change the base URL

Turn on Override OpenAI Base URL and write:

https://api.helmcode.com/v1

4. Add the models

With Add Model, write the id exactly as it appears in Models:

glm5.3-flash
deepseek-v4-flash
qwen3.6

The names Cursor ships with do not exist on Helmcode, so turn them off or ignore them. If you leave one of them selected, the request goes out with an id the API does not recognize and comes back a 401 saying your key has no access to that model — which reads like a plan problem and is really a name problem.

5. Verify

Press Verify so Cursor checks the connection, then open the chat panel, pick one of the models you added and ask it something.

To be completely sure, look at your usage in the console: if the tokens go up, the requests are arriving.

glm5.3-flash for agent mode, where the 1M context is what matters, and deepseek-v4-flash as the other 1M model on the same quota. qwen3.6 if answers feel slow and you would rather have speed than depth. All three take screenshots.

Known issues

  • Inline autocomplete does not use Helmcode. It is Cursor’s own and cannot be redirected. If what you want is for inline suggestions to come out of Helmcode, the tool is Zed, which does allow it.
  • The option is not on every plan. In some recent versions it only shows up on certain plans. The remaining alternative is then the Azure-style configuration, if your version has it.
  • It is a global override. Once you change the base URL, everything Cursor used to send to OpenAI goes to Helmcode. It is not a per-model selection.
  • Features that run on Cursor’s servers do not move. Whatever Cursor processes on its own infrastructure stays as it is.