Run Open WebUI on Mingles Router
Open WebUI treats any OpenAI-compatible server as a connection: set the API base URL and key, and the model list fills itself from /v1/models.
Pick your model and paste your key — every command and value on this page updates live.
Endpoint: https://router.mingles.ai/v1 · key stays in your browser ·
no key entered? commands show <your-key>.
Two ways to connect
1. In the UI
Admin Panel → Settings → Connections → OpenAI API: paste the base URL and key, save. Models appear in the picker automatically.
2. Or at docker run
Bake it into the container instead:
docker run -d -p 3000:8080 \
-e OPENAI_API_BASE_URL="https://router.mingles.ai/v1" \
-e OPENAI_API_KEY="<your-key>" \
-v open-webui:/app/backend/data \
ghcr.io/open-webui/open-webui:main3. Pick a model and chat
Both models arrive from /v1/models. Kimi for quality, MiniMax when volume matters.
Exact values
| Where | Admin Panel → Settings → Connections |
| OpenAI API Base URL | https://router.mingles.ai/v1 |
| API Key | <your-key> |
Switch model
Multiple connections coexist — keep Ollama for local models and this endpoint for cloud-grade ones.
Before you file a bug: read the limits
Reasoning models spend the output budget on internal thinking, output is capped at 8192 tokens, there is no KV cache, and there are no built-in web tools. Most “it broke on Mingles Router” reports are one of these. See Model limits & behavior →
Frequently asked
Can I keep my local Ollama models too? +
Yes. Connections are additive; the model picker shows everything from every source.