Skip to content
All docs

Apps

KoboldAI Lite setup

KoboldAI Lite runs in your browser and can use any OpenAI-compatible API. nokeep allows calls straight from the browser, so it connects with no extra proxy.

Checked 26 October 2026

The values

Custom 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

  1. Open KoboldAI Lite and its AI provider settings.
  2. Choose the OpenAI-compatible API provider.
  3. Paste https://nokeep.ai/v1 as the URL and sk-nokeep-test as the key.
  4. Fetch the model list and pick deepseek-v4.1-flash-uncensored. Use the chat completions mode if the provider offers a choice.
  5. Send a message. A reply that starts “Connected to” means the setup works.
  6. Swap in your own key from the console.

If it doesn’t connect

The app showsFix
401The key is wrong or revoked. Paste it again, with no spaces or quotes.
404The URL is wrong. Use https://nokeep.ai/v1 exactly.
402Your account is out of bought credits. Top up in the console, from $5.
429Over 120 requests a minute, or the key’s daily cap. Raise the cap in the console, or wait.
503The model is busy. Send again in a few seconds; nothing was charged.
The fixed test lineThe setup works. Swap in your own key to get real replies.

Every error is listed with its fix in Errors.

What an evening costs

At 3,000 tokens in and 250 out a reply, $5 is about 2,700+ replies on DeepSeek, or 6,500+ replies on GLM. A longer character card or a longer chat history costs more per reply, since the whole history is sent each time. Work out your own.