Apps
Wyvern setup
Wyvern lets you add a custom provider that speaks OpenAI’s API format. Add nokeep as that provider, give it a key, and pick an uncensored model for your connection.
Checked 29 October 2026
The values
- API 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 AI Connections, under Account in the sidebar, and go to the Providers tab.
- Press Create Provider. Name it nokeep, set API URL Type to OpenAI, and turn on Chat Completion Only.
- Paste
https://nokeep.ai/v1as the API URL, and save the provider. - Press Add API Key on the new provider and paste
sk-nokeep-test. Wyvern checks the key as you add it. - Go to the Connections tab and press New. Give it a name and choose the nokeep provider.
- Turn on Force Chat Completion, press Fetch Models, and pick
deepseek-v4.1-flash-uncensored. - Send a message to a character. A reply that starts “Connected to” means the setup works.
- Replace the provider’s key with your own from the console.
Start with https://nokeep.ai/v1. If fetching the models or the first message answers 404, use the full https://nokeep.ai/v1/chat/completions instead: setups differ on which one this field wants.
Labels can move between Wyvern versions. If one isn’t where this says, look in the same panel.
Samplers and settings
- DeepSeek takes Wyvern’s Temperature, Top P, Top K and Min P. Min P at 0.05 with a temperature near 0.9 is a good start: Samplers for fiction.
- If the provider form asks which parameters to allow, allow those four and Max Tokens.
- DeepSeek answers at once unless asked to think, so Wyvern’s Max Tokens is all reply.
- Wyvern sends calls from its own servers unless you turn on Use Browser Request. Either way works: nokeep accepts calls from a browser too.
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 path is missing or doubled. Try https://nokeep.ai/v1, or https://nokeep.ai/v1/chat/completions if the base answers 404. |
| 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.
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.
Questions
Is this the same as Wyvern’s free queue?
No. With a custom provider, Wyvern sends your chat to the model you pick, here DeepSeek V4.1 Flash or GLM 5.3 Flash with their refusals removed, billed to your nokeep credits.
Does Wyvern see my nokeep key?
The key is saved with the provider in your Wyvern account, so it can call the API for you. Give Wyvern its own key with a daily cap, and revoke it in the console if you stop using it.