Skip to main content
Open WebUI is a self-hosted web interface for chatting with models. Beyond Ollama it works with any OpenAI-compatible API, so RuAPI connects as an OpenAI connection — just an address and a key.

​
Prerequisites

1

RuAPI account and API key

Console → Tokens → create an sk-... key. The balance tops up in USDT — see Top-up.
2

A running Open WebUI

Install per the Open WebUI docs (usually Docker).

​
Option 1: through the UI

1

Open connection settings

Admin Panel → Settings → Connections (or Settings → Connections for the current user).
2

Add an OpenAI connection

Enable the OpenAI API and enter:
FieldValue
API Base URLhttps://www.ruapi.ai/v1  — with /v1
API Keysk-your-key
Save. Open WebUI pulls the model list via /v1/models.

​
Option 2: through environment variables

When starting the container, set: 
docker run -d -p 3000:8080 \
  -e OPENAI_API_BASE_URL=https://www.ruapi.ai/v1 \
  -e OPENAI_API_KEY=sk-YOUR_KEY \
  -v open-webui:/app/backend/data \
  --name open-webui ghcr.io/open-webui/open-webui:main

​
Verify

Start a new chat, pick a model (e.g. claude-opus-4-8) and send a message. A reply plus an entry in RuAPI Console → Logs means it works.

​
Troubleshooting

  • Check the Base URL is https://www.ruapi.ai/v1 with /v1: models are fetched via /v1/models.
  • The key must be a RuAPI token (sk-...).
The key is wrong or has spaces. Check its state in RuAPI Console → Tokens.
You can: Open WebUI supports several connections at once. Local Ollama models and cloud RuAPI models show up in the same picker.