Skip to main content

OpenWebUI

Integrate OpenWebUI with AI Studio through the OpenAI-compatible API.

This quickstart guide shows you how to integrate OpenWebUI with Hyperstack AI Studio using the OpenAI-compatible API. You’ll learn how to install OpenWebUI, generate API credentials from AI Studio, configure an OpenAI provider connection, and activate your selected model. This setup enables OpenWebUI to interact with any base or fine-tuned model hosted in AI Studio through a secure API endpoint.

Full Guide

For the complete guide that includes architecture details and advanced configuration, see How to Connect Hyperstack LLMs to OpenWebUI in Minutes.

Why Integrate OpenWebUI with Hyperstack AI Studio​

OpenWebUI is an open-source, browser-based interface for interacting with large language models. It provides a clean chat interface, multi-user support, and compatibility with OpenAI-style APIs.

Hyperstack AI Studio is a fully managed LLM platform that offers scalable inference, fine-tuning capabilities, and OpenAI-compatible endpoints. This makes it a powerful backend for OpenWebUI, allowing you to connect directly to production-grade models without managing infrastructure.

By integrating OpenWebUI with AI Studio, you can:

  • Use a self-hosted chat interface for model interaction
  • Connect to base or fine-tuned Hyperstack models
  • Switch models by updating API credentials
  • Avoid managing GPUs or inference infrastructure

To learn how to integrate OpenWebUI with AI Studio end-to-end, see the quickstart tutorial below, or view the full guide: How to Connect Hyperstack LLMs to OpenWebUI in Minutes.

How to Install and Connect OpenWebUI to Hyperstack AI Studio​

Follow these steps to install OpenWebUI and connect it to Hyperstack AI Studio. For deeper background and extended configuration details, see the OpenWebUI full integration guide.

  1. Install OpenWebUI​

    You can install OpenWebUI using Docker or Python. Docker is recommended.

    Option A: Docker

    docker pull ghcr.io/open-webui/open-webui:main
    docker run -d -p 3000:8080 -v open-webui:/app/backend/data --name open-webui ghcr.io/open-webui/open-webui:main

    Access the interface at: http://localhost:3000

    Option B: Python

    python3 -m venv venv
    source venv/bin/activate  # macOS/Linux
    # venv\Scripts\activate  # Windows

    pip install open-webui
    open-webui serve

  2. Create an Administrator Account​

    a. Open http://localhost:3000
    b. Click Get Started
    c. Register your first user account

    The first registered user becomes the Administrator and can configure API connections.

  3. Get API Credentials from Hyperstack AI Studio​

    Generate the required credentials to authenticate OpenWebUI with AI Studio.

    a. Log in to the Hyperstack Console
    b. Navigate to the AI Studio Playground
    c. Retrieve the OpenAI-compatible Base URL: https://console.hyperstack.cloud/ai/api/v1
    d. Select your desired model (for example openai/gpt-oss-120b)
    e. Visit the API Keys page and create a new key
    f. Copy and securely store the generated API key

  4. Configure OpenWebUI Provider Connection​

    a. In OpenWebUI, click your Profile icon
    b. Navigate to Settings → Connections
    c. Click Add New Connection
    d. Select OpenAI API as the provider

    Enter the following:

    • Base URL: https://console.hyperstack.cloud/ai/api/v1
    • Model Name: openai/gpt-oss-120b
    • API Key: Your Hyperstack API key

    Click Save.

  5. Activate the Model​

    a. Click New Chat
    b. Open the model selector dropdown
    c. Choose your configured Hyperstack model

    The model is now active.

  6. Run and Test​

    Send a test prompt such as:

    Write a Python function that returns "Hello, World!"

    Confirm that the response is returned from your Hyperstack AI Studio-hosted model.

    Next Steps

    For troubleshooting, deployment recommendations, and advanced configuration, see the full guide: How to Connect Hyperstack LLMs to OpenWebUI in Minutes.


Back to top

On this page