Use DeepSeek in Open WebUI, LobeChat and Chatbox
Updated 2026-10-18 · Add an OpenAI-compatible provider to three popular chat apps for the web, desktop and mobile.
Connection details
- Base URL (OpenAI compatible)
- https://api.aifans.fan/v1
- API key
- Create one in the console; it starts with sk- (no account yet? sign up)
- Recommended models
- deepseek-v4.1-flash, deepseek-v4-pro (all models and prices)
Open WebUI, LobeChat and Chatbox are popular chat apps for the browser, the desktop and mobile. Each lets you add an OpenAI-compatible provider.
Open WebUI
- Admin Panel → Settings → Connections, and add an OpenAI API connection.
- URL https://api.aifans.fan/v1, key your API key. Save; the model list loads from our /v1/models.
- Pick deepseek-v4.1-flash in a new chat.
LobeChat
- Settings → AI Service Provider, choose OpenAI (or add a custom OpenAI-compatible provider).
- API key your key, API proxy address https://api.aifans.fan/v1.
- Fetch the model list or add deepseek-v4.1-flash by hand, then run the connectivity check.
Chatbox
- Settings → Model Provider → add a custom provider, API mode “OpenAI API Compatible”.
- API host https://api.aifans.fan, API path /v1/chat/completions, API key your key.
- Add deepseek-v4.1-flash to its models and select it in a new chat.
Menu names change between versions. If an app rejects the address, try https://api.aifans.fan instead of https://api.aifans.fan/v1 or the other way round.
Tips
- DeepSeek and some other models think before they answer, and thinking counts as output tokens. For small talk a model without thinking is cheaper; see Models.
- When several people share one app, give each person a key with a spending limit; the console shows usage per key.