Apps
Open WebUI setup
Open WebUI takes any OpenAI-compatible API as a connection. Add nokeep once and both uncensored models show up in the picker, beside your local ones.
Checked 26 October 2026
The values
- API Base URL
https://nokeep.ai/v1- API key
sk-nokeep-test to test, then your own sk-nokeep-… key- Model
deepseek-v4.1-flash-uncensored
Start with the free test key: it answers one fixed line, which proves the setup is right without spending anything. Then paste your own key from the console. deepseek-v4.1-flash-uncensored for most chats and pictures, or glm-5.3-flash-uncensored for text at under half the price.
Connect
- Open the Admin Panel, then Settings, then Connections.
- Under the OpenAI API connections, add a new one.
- Paste
https://nokeep.ai/v1as the URL andsk-nokeep-testas the key, and save. - Start a new chat and pick
deepseek-v4.1-flash-uncensoredfrom the model picker. Send a message: a reply that starts “Connected to” means it works. - Edit the connection and swap in your own key from the console.
Open WebUI reads the model list from our /v1/models. If the models don’t appear, check the URL ends in /v1.
Why it suits a self-hosted setup
Your chats stay in your Open WebUI. Each call sends the conversation to the model and back; we keep one row of counts per call, never the words. What we keep.
If it doesn’t connect
| The app shows | Fix |
|---|---|
| 401 | The key is wrong or revoked. Paste it again, with no spaces or quotes. |
| 404 | The URL is wrong. Use https://nokeep.ai/v1 exactly. |
| 402 | Your account is out of bought credits. Top up in the console, from $5. |
| 429 | Over 120 requests a minute, or the key’s daily cap. Raise the cap in the console, or wait. |
| 503 | The model is busy. Send again in a few seconds; nothing was charged. |
| The fixed test line | The setup works. Swap in your own key to get real replies. |
Every error is listed with its fix in Errors.