Open WebUI

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

RuAPI account and API key

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

A running Open WebUI

Install per the Open WebUI docs (usually Docker).

Option 1: through the UI

Open connection settings

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

Add an OpenAI connection

Enable the OpenAI API and enter:

Field	Value
API Base URL	`https://www.ruapi.ai/v1` — with `/v1`
API Key	`sk-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

The model list is empty

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-...).

401 / auth error

The key is wrong or has spaces. Check its state in RuAPI Console → Tokens.

I want to keep both Ollama and RuAPI

You can: Open WebUI supports several connections at once. Local Ollama models and cloud RuAPI models show up in the same picker.

Getting Started

Guides

API Reference

Model guides

Integrations

Capabilities

Recipes

Legal

Prerequisites

Option 1: through the UI

Option 2: through environment variables

Verify

Troubleshooting

​Prerequisites

​Option 1: through the UI

​Option 2: through environment variables

​Verify

​Troubleshooting

Prerequisites

Option 1: through the UI

Option 2: through environment variables

Verify

Troubleshooting