Use Nivana in Open WebUI

Open WebUI talks to any OpenAI-compatible API. Add Nivana as a connection and one model, nivana/auto, answers every chat with whichever model scores best for it.

What you need

  • A Nivana API key: sign in, open the account menu and choose API keys. New accounts get 2,000 free credits.
  • The base URL https://nivana.one/v1 and the model name nivana/auto (or nivana/quality, nivana/speed, nivana/cost to lean the router one way).

Set up Open WebUI

  • Open Admin Settings → Connections, and under OpenAI API add a connection.
  • URL: https://nivana.one/v1. Key: your Nivana key. Save; Open WebUI reads the model list from /v1/models.
  • Pick nivana/auto in the model menu and start a chat.

Running it in Docker, you can set the same thing with environment variables:

docker run -d -p 3000:8080 \
  -e OPENAI_API_BASE_URL=https://nivana.one/v1 \
  -e OPENAI_API_KEY=nvn_sk_… \
  ghcr.io/open-webui/open-webui:main

Limits

Tool calling works: the client’s tools are passed to the routed model, which can call them, and each step is routed on its own. JSON mode and sampling parameters (temperature, max tokens) are ignored, Nivana’s own web search is off when the client sends tools, and very long tool histories are not summarised, so a request larger than every model’s context window fails.

Every response’s model field names the model that actually answered. See the OpenAI-compatible endpoint and how routing works.