← All applications · Connect apps section on /docs
OpenAIManual setup
Open WebUI
Open WebUI: configure a provider for a self-hosted chat interface.
Published instructions · App version: unverified
Chat, ping, invoke and content-generation examples may send real billable requests. Check the model, balance, rate and minimum before running them. GET /v1/models checks authentication and the catalogue only. Set up environment variables safely
Base URL to paste
OpenAI SDKs generally use a URL ending in /v1; Anthropic SDKs use the root URL. Avoid adding /v1 twice. Protocol compatibility does not guarantee every provider feature.
https://thapi.cloud/v1Prerequisites
- Docker
- API key ThAPI
Recommended model: gpt-5.6-sol
Quick way — command / config
Admin → Settings → Connections → OpenAI API
API Base URL : https://thapi.cloud/v1
API Key : sk-thapi-...
→ Save → reload trangWhere to place file / fill Settings
Dockerany
biến môi trường container
OPENAI_API_BASE_URL=https://thapi.cloud/v1 OPENAI_API_KEY=sk-thapi-...
Verify connection
- Open http://localhost:3000 — ThAPI models appear after GET /v1/models.
- Send a chat message and check Dashboard Usage.
Troubleshooting
| Symptom | Reason | How to handle |
|---|---|---|
| Model not visible | Base URL is missing /v1 or the key is invalid. | Đúng https://thapi.cloud/v1; kiểm tra key. |
Notes
- Open WebUI fetches /v1/models automatically — no need to declare each model manually.