Open WebUI is the most popular self-hosted AI interface, an extensible workspace that teams run on their own infrastructure, offline if needed. It connects to OpenAI-compatible APIs out of the box: add a connection with a base URL and key and the models behind it appear for your users. Connect Opper and one admin setting gives your whole deployment 700+ models, with a choice of EU or US inference behind your own walls.
Open WebUIoninPaste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.
Qwen3 Coder 480B A35B Instruct Turbo runs on the routes below. Route only to EU providers when your data has to stay in Europe. Its route also sells flex processing: the same model at another price, picked per request with service_tier. How service tiers work.
| Provider | Region | Zero data retention | Training | Input | Output | Cache read | |
|---|---|---|---|---|---|---|---|
| US | No | $0.30 | $1.00 | $0.10 |
Qwen3 Coder 480B A35B Instruct Turbo by Alibaba, a throughput-optimized 262K-context variant of the 480B coding model for faster inference.
Step-by-step setup for running Open WebUI on each of these models through Opper.
A secure AI workspace for companies: 25+ leading models, projects and connectors in one GDPR-compliant platform, hosted in Europe.
built on Opper
The leading open-source AI chat platform. One librechat.yaml block connects it to every model on Opper.
OpenAI-compatibleAsk a question and let a panel of leading AI models vote, debate, and reach consensus, side by side in one place.
by Opper