Integrations

Open WebUI

Connect Open WebUI to Qubrid AI models through the OpenAI-compatible API

Open WebUI is a self-hosted web interface for chatting with AI models. Connect it to Qubrid AI to use Qubrid-hosted models from your own Open WebUI dashboard with a standard OpenAI-compatible endpoint.

Video tutorial

Prerequisites:

Install Open WebUI

If you have not installed Open WebUI yet, follow the Open WebUI quick start guide for Docker, pip, or other supported installation methods.

After installation, open your Open WebUI dashboard in a browser. The host and port depend on your setup (for example http://127.0.0.1:8080 or http://127.0.0.1:8081).

Generate your Qubrid AI API key

Log in to the Qubrid AI Platform

Sign in to your account on the Qubrid AI Platform.

Open API Keys

In the top navigation bar, click API Keys.

Create a new API key

Click Create API Key.

Give your key a name and description, then click Generate.

Copy and store your API key

Copy the key and store it somewhere safe.

Your API key is shown only once for security. If you lose it, you must generate a new key from Manage API Keys.

Configure the connection in Open WebUI

Open Open WebUI admin settings

Open your Open WebUI dashboard in a browser and log in with your admin account.

Click your profile icon in the bottom-left corner and go to Admin Settings.

You can also open the connections page directly if you know your instance URL, for example:

http://127.0.0.1:8080/admin/settings/connections

The host, port, and path depend on how you installed Open WebUI.

Open the Connections tab

In Admin Settings, select the Connections tab.

Enable the OpenAI API connection

Under the OpenAI API section (or by adding a new connection), toggle it ON.

Enter the Qubrid API base URL and key

Enter the following details:

FieldValue
API Base URLhttps://platform.qubrid.com/v1
API KeyYour Qubrid AI API key from the previous section

Click the Save icon (or the refresh button next to it) to verify the connection. Open WebUI will automatically pull the available models from Qubrid AI.

Use Chat Completions and leave model names empty

Leave the API mode set to Chat Completions.

Do not add individual model names in the connection settings. Leaving the model list empty allows Open WebUI to load all relevant models exposed by the Qubrid endpoint.

Select and chat with your model

Return to the main chat interface

Go back to the main chat screen in Open WebUI.

Open the model dropdown

Start a new chat and click the model dropdown at the top of the chat window.

Choose a Qubrid-hosted model

Select your preferred Qubrid-hosted model from the list. Examples include:

  • openai/gpt-oss-120b
  • Qwen/Qwen3.7-Max

Browse the full catalog and copy exact model strings from Serverless Models. Model IDs are case-sensitive.

Start chatting

Send a test prompt to confirm responses are coming from Qubrid.

Your Qubrid integration with Open WebUI 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-running or high-volume sessions.
  • Rotate API keys if you suspect a key was exposed.

Configuration reference

SettingValue
API Base URLhttps://platform.qubrid.com/v1
API KeyYour Qubrid API key
API modeChat Completions
Model names in connectionLeave empty to load all models from the endpoint
Example modelopenai/gpt-oss-120b

Model strings vary by model-always copy the API model string from Serverless Models.

Frequently Asked Questions (FAQ)

Go to Open WebUI Docs

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