Apps
Tavo setup
Tavo, the roleplay app for phones, takes any API that speaks OpenAI’s protocol. Add nokeep as a new connection and your characters run on an uncensored model.
Checked 29 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
- Tap the button in the top left corner, then API Connections, then New Connection.
- Set Model Platform to Custom (OpenAI Protocol).
- Paste
sk-nokeep-testas the API Key. - Paste
https://nokeep.ai/v1as the API Base URL. Stop at/v1. - Type
deepseek-v4.1-flash-uncensoredas the Model Name, exactly as written. - Save, and set the connection as your default.
- Send a message to a character. A reply that starts “Connected to” means the setup works.
- Edit the connection and swap in your own key from the console.
Tavo wants the base URL. If a call fails with 404, check the URL ends in /v1, not /chat/completions.
Settings worth knowing
- Tavo calls the API straight from your phone. Your chats stay in the app; we keep one row of counts per call, never the words.
- DeepSeek answers at once unless asked to think, so a short reply length still gets a whole paragraph back.
- DeepSeek takes temperature and the other samplers. Good starting values are on Samplers for fiction.
- Phone data is fine: a reply is a few kilobytes, streamed as it is written.
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 missing /v1 or has the path twice. Use https://nokeep.ai/v1. |
| 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
Do I need a jailbreak prompt in Tavo?
No. Both models have their refusals removed from the weights, so characters stay in character without one.
Can I use GLM instead?
Yes: type glm-5.3-flash-uncensored as the Model Name. It costs under half as much per token, reads text only, and thinks briefly before each reply.