Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.platform.qubrid.com/llms.txt

Use this file to discover all available pages before exploring further.

Connect Cursor to Qubrid AI by adding Qubrid as an OpenAI-compatible model provider. After setup, you can select Qubrid models from the Cursor chat and use AI-powered coding assistance with your Qubrid endpoint and API key.
Prerequisites:

​
Configure Qubrid AI in Cursor

1

Open Cursor Settings

Open Cursor Settings from the Cursor menu or with Ctrl+, on Windows/Linux and Cmd+, on macOS.
2

Go to the Models tab

In the settings panel, open the Models tab.
3

Uncheck existing models

Uncheck every model in the list so Cursor does not route requests to built-in providers. This ensures your custom Qubrid model is used when you select it in chat.
4

Open the API Keys section

Scroll down to API Keys and click the down arrow to expand the section.
5

Enable the OpenAI API Key

Enable the OpenAI API Key section so you can enter your Qubrid credentials.
6

Generate and paste your Qubrid API key

  1. Open the Qubrid AI Platform and generate an API key. Follow How to generate an API Key.
  2. Return to Cursor and paste the key into Enter your OpenAI API Key.
Your API key is shown only once for security. Store it somewhere safe and secure before closing the dialog. If you lose it, you must generate a new key.
7

Override the OpenAI base URL

Turn on the toggle for Override OpenAI Base URL and paste the Qubrid base URL:
https://platform.qubrid.com/v1
8

View all models and add a custom model

Scroll up slightly and click View all models, then select + Add Custom Model.
9

Enter the Qubrid model ID

Enter the Model ID for the model you want to use.You can find the model ID on the model page on the Qubrid platform, right beside the model name-click the copy button to copy it exactly.For example, Qwen 3.7 Max uses:
Qwen/Qwen3.7-Max
You can also copy the model ID from the AI Playground under the Serverless endpoint section. The ID must match exactly or the model will not work in Cursor.
10

Select your Qubrid model in chat

Open the Cursor chat screen. Click the pill that says Auto, turn the toggle off, then select the custom model you just added.You can now use Cursor with your Qubrid model. Send a test prompt to confirm responses are coming from Qubrid.
Your Qubrid integration with Cursor is now configured.

​
Monitor usage on Qubrid

Keep an eye on your usage and costs on the Qubrid platform.
  • Review Inference Logs to see request history and debug issues.
  • Check your credit balance before long or high-volume coding sessions.
  • Rotate API keys if you suspect a key was exposed.

​
Configuration reference

SettingValue
OpenAI API KeyYour Qubrid API key
Override OpenAI Base URLhttps://platform.qubrid.com/v1
Example model IDQwen/Qwen3.7-Max
Model IDs vary by model-always copy the ID from the model page or Playground.

​
Frequently Asked Questions (FAQ)

Confirm the following:
  • OpenAI API Key is your valid Qubrid API key (regenerate from Manage API Keys if needed)
  • Override OpenAI Base URL is exactly https://platform.qubrid.com/v1
  • Other models are unchecked in the Models tab so Cursor does not fall back to a different provider
Make sure you:
  • Added the model with + Add Custom Model and used the exact model ID from the platform or Playground
  • Opened chat, clicked the Auto pill, and turned the toggle off
  • Selected your custom Qubrid model from the list
If the model ID is wrong, Cursor will not connect to Qubrid successfully.
In the chat panel, click the Auto pill and turn the toggle off. Then manually select your custom Qubrid model.Also confirm every other model is unchecked under Cursor Settings → Models so Cursor does not route to a default provider.
The model ID must match the value on the Qubrid model page or in the Playground Serverless endpoint field-for example Qwen/Qwen3.7-Max. IDs are case-sensitive and include the provider prefix (such as Qwen/ or openai/).Copy the ID with the copy button on the platform rather than typing it manually.
Check your network connection and confirm the Qubrid endpoint is reachable. Review the model’s expected response time in the AI Playground.Use Inference Logs to see whether requests are failing or taking longer than expected on the platform side.
Open Inference Logs on the Qubrid platform to review API usage, monitor spend, and troubleshoot failed requests.

Go to Cursor Docs

If you have any questions related to Cursor, this is your place to be