Cursor with your own model: Qwen and GLM with no request limits

Why connect it

Cursor lets you set your own key and an OpenAI-compatible base URL. Chat and agent requests to that model then go through Tenzo Cloud on your subscription.

This helps when your Cursor plan limits run out or you need a specific model, such as Qwen 3.8 Max with a large context for a big project.

How to connect Cursor

You need a key from the dashboard: 3 free hours start right after sign-up. Replace tc-your-key with your key.

1. 1

   Get a key

   Create a key in the Tenzo Cloud dashboard under API keys.

2. 2

   Open model settings

   In Cursor open Settings → Models.

3. 3

   Set the key and address

   Paste the key into OpenAI API Key, enable Override OpenAI Base URL and enter the Tenzo Cloud address.

   Cursor → Settings → ModelsCopy

   OpenAI API Key:           tc-your-key
   Override OpenAI Base URL: https://tenzo-cloud.com/v1
   Add model:                qwen-3.8-max

4. 4

   Add the model

   Add a model with the id from the example and enable it in the list. Pick it in chat or agent mode.

Common errors and fixes

The model does not show up in the list

Add it manually by id (for example qwen-3.8-max) and turn on the toggle next to it.

Autocomplete works as before

Cursor’s built-in autocomplete uses Cursor’s own models. Your model is used in chat and agent mode.

401 invalid_api_key, “key not found”

Make sure the whole key is copied with no spaces or quotes and is enabled in the dashboard. Expired keys also return 401.

403 no_access, “no access to this model”

There is no active subscription for this model, or the key does not allow this model or your IP. Check Plans and the key restrictions in the dashboard.

404 model_not_found

The model id is wrong. Use an id from the model list, for example qwen-3.8-max or glm-5.3.

429 concurrency_limit

All your streams are busy or you exceeded 120 requests a minute. Retry in a few seconds or buy more streams, they stack.

503 model_unavailable

The model is under maintenance. Each model’s status is on the status page; switch models with one line.