Do I need to expose Ollama separately?

Expose Open WebUI

Share your local Open WebUI (ChatGPT-like interface for Ollama) with anyone.

Open WebUI is a self-hosted ChatGPT-style frontend for Ollama and other LLM backends. It runs on port 3000 (or 8080).

Start Open WebUI (typically via Docker: docker run -p 3000:8080 ghcr.io/open-webui/open-webui:main).

Run the Skytunnel command with the host port (3000).

Share the public URL — anyone can chat with your local LLMs through a clean web interface.

No, if Open WebUI connects to Ollama via localhost inside Docker's network. Only expose the Open WebUI port.