Set Up Open WebUI for Free Using a Community LLM API Key

What Is Open WebUI?

Open WebUI is a self-hosted, open-source web interface for interacting with large language models. Think of it as your own private ChatGPT — running on your machine, with no usage limits tied to a subscription, and with full control over which models you connect to. It supports multiple backends, conversation history, custom system prompts, model switching mid-conversation, and even image generation.

The best part: combined with a FreeLLMKeys API key, you can run Open WebUI for free and access GPT-4o, Claude, Gemini, DeepSeek, and 90+ other models from a single beautiful interface.

Prerequisites

• Docker installed on your machine (get Docker here)
• A free API key from FreeLLMKeys.com
• About 5 minutes of setup time

Install Open WebUI with Docker

Run this single command in your terminal:

docker run -d \
  -p 3000:8080 \
  --add-host=host.docker.internal:host-gateway \
  -v open-webui:/app/backend/data \
  --name open-webui \
  --restart always \
  ghcr.io/open-webui/open-webui:main

Wait about 30–60 seconds for the container to start, then visit http://localhost:3000 in your browser. You will see the Open WebUI setup screen.

Create Your Admin Account

On first launch, Open WebUI will ask you to create an admin account. Fill in a username, email, and password (these are local only — nothing is sent to any external server). Click Create Account.

Configure the Custom API Endpoint

This is where you connect FreeLLMKeys:

1. Click your profile icon in the top right → Admin Panel
2. Go to Settings → Connections
3. Under OpenAI API, click the toggle to enable it
4. Set the API Base URL to: https://aiapiv2.pekpik.com/v1
5. Set the API Key to your FreeLLMKeys key (e.g., sk-xxxxxxxx)
6. Click Save

Add Models to the Model Selector

After saving your connection settings, go back to the main chat screen. Click the model dropdown at the top of the chat window. Open WebUI will automatically detect available models from the endpoint. You should see GPT-4o, Claude Opus, Gemini, DeepSeek, and others listed.

Select any model and start chatting. You can switch models mid-conversation from the same dropdown.

Share Open WebUI with Your Team or Family

Want to give your teammates or family members access to your Open WebUI instance? The easiest approach is Tailscale:

1. Install Tailscale on your host machine and your teammates' machines
2. Join the same Tailscale network
3. Share your machine's Tailscale IP — they can access Open WebUI at http://[your-tailscale-ip]:3000

This gives you a private, secure ChatGPT alternative that your whole team can use — connected to 90+ free AI models — at zero monthly cost.

Open WebUI vs Using ChatGPT Directly

The self-hosted approach is not for everyone — it requires Docker and a bit of initial setup. But if you are a developer who values privacy and wants access to multiple models, Open WebUI with FreeLLMKeys is one of the best free setups available.