Open WebUI self-hosted ChatGPT-style interface (135k stars): connects to Ollama, LiteLLM, and remote APIs. Custom branding-preserving license — note the terms.
Open WebUI is a self-hosted ChatGPT-style interface that connects to Ollama, LiteLLM, and remote APIs. These guides cover deploying it and noting its branding-preserving license terms.
It gives teams a private chat front end over local or remote models. Apify data can flow into the models it serves. Below you will find setup guides for Open WebUI.
ChatGPT Team costs $25 per user per month. At 10 users that is $3,000 per year — before you factor in rate limits, data residency concerns, and the fact that every prompt you send trains future OpenAI models unless you opt out. Self-hosting an LLM stack eliminates per-seat costs, keeps prompts on hardware you control, and lets you run models tuned for your domain.
TL;DR
docker-compose.yml: Ollama + LiteLLM + Open WebUI + Authentik + PostgreSQL + Redis + CaddyEvery prompt your team sends to ChatGPT Team or Copilot for Microsoft 365 leaves your network and is processed on OpenAI's or Microsoft's servers. For most teams that's an acceptable trade-off. For teams handling legal documents, source code, financial data, or customer PII, it is not. This guide deploys a private ChatGPT equivalent — Llama 3 70B running on your own GPU hardware, with a ChatGPT-quality web interface, your company's SSO, and per-team usage budgets — entirely inside your infrastructure.
Open WebUI is a self-hosted ChatGPT-style interface with 135k+ GitHub stars. It connects to Ollama for local model inference, LiteLLM for multi-provider routing, and any OpenAI-compatible API. Run it on a Liquid Web Managed VPS (CPU-only for remote APIs) or a Liquid Web GPU server when pairing with Ollama for fully local inference.
Open WebUI itself is light — 1–2 GB RAM is enough. The RAM and GPU requirements come from the model backend. For Ollama with 7B models, a Liquid Web 8 GB VPS with a consumer-class GPU works; for 70B models, a Liquid Web L40S (48 GB VRAM) is recommended. If you only proxy to remote APIs via LiteLLM, a 4–8 GB CPU VPS is sufficient.
Open WebUI uses a custom branding-preservation license: free for personal, internal, and commercial use as long as the Open WebUI branding remains visible. Removing or replacing the branding (whitelabel) requires a paid license. Always re-read the current terms on the project's GitHub before a production rollout — license terms can change.