Integration · 60-second setup · Zero markup
Open WebUI + OrcaRouter
Open WebUI is the most popular self-hosted LLM chat interface. It reads its OpenAI connection from two environment variables — start the container with them pointed at OrcaRouter and every model on the catalog shows up in the model picker.
Setup
Five steps.
- 1.Install Docker (or use an existing Open WebUI deployment).
- 2.Start the container with OPENAI_API_BASE_URL=https://api.orcarouter.ai/v1 and OPENAI_API_KEY=sk-orca-… (see the snippet).
- 3.Open http://localhost:3000 and create the admin account.
- 4.Every OrcaRouter model appears in the model picker automatically — or manage the connection later under Admin Panel → Settings → Connections.
- 5.Pick a model and chat. You're routing.
Configuration
docker run -d -p 3000:8080 \ -e OPENAI_API_BASE_URL="https://api.orcarouter.ai/v1" \ -e OPENAI_API_KEY="sk-orca-..." \ -v open-webui:/app/backend/data \ --name open-webui \ ghcr.io/open-webui/open-webui:main
Why route Open WebUI through OrcaRouter?
Open WebUI is only as good as the endpoint behind it. With OrcaRouter you give every user of your instance 200+ models through one connection, automatic failover when a provider goes down, and a single cost dashboard instead of a drawer full of API keys.
Other integrations
⌘ Cursor
AI-first code editor.
🤖 Cline
Autonomous coding agent for VS Code.
➡ Continue
Open-source AI code assistant for VS Code and JetBrains.
✎ Aider
AI pair programming in your terminal.
▲ Vercel AI SDK
Streaming AI for TypeScript apps.
🦜 LangChain
Compose LLM apps in Python or JS.
🦙 LlamaIndex
Data framework for LLM applications.
✳ Claude Code
Anthropic's terminal coding agent.
⚙ n8n
Workflow automation with native AI nodes.
Route Open WebUI through OrcaRouter today.
Sign up in under a minute, grab an sk-orca-… key, and paste it into Open WebUI. Zero markup on tokens. Automatic failover across every provider.
