NeverSleep API
Access NeverSleep instantly with Puter.js, and add AI to any app in a few lines of code without backend or API keys.
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain AI like I'm five!", {
model: "neversleep/llama-3.1-lumimaid-8b"
}).then(response => {
console.log(response);
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain AI like I'm five!", {
model: "neversleep/llama-3.1-lumimaid-8b"
}).then(response => {
console.log(response);
});
</script>
</body>
</html>
List of NeverSleep Models
Lumimaid v0.2 8B
neversleep/llama-3.1-lumimaid-8b
Lumimaid v0.2 8B is a roleplay and creative writing model created by NeverSleep (IkariDev and Undi), fine-tuned on Meta's Llama 3.1 8B Instruct. It offers a 32,768-token context window. Version 0.2 represents a significant dataset overhaul from v0.1, with aggressive cleanup of low-quality and repetitive outputs. Roughly 40% of its training data is non-roleplay, giving it solid general conversational ability alongside its creative strengths. The model is best suited for interactive fiction, character-driven dialogue, and long-form creative text generation. Its 8B parameter size keeps inference costs low while delivering expressive, stylistically consistent output. A good pick for developers building chat-based storytelling or companion apps who need a capable small model with a generous context window.
ChatNoromaid 20B
neversleep/noromaid-20b
Noromaid 20B is a 20-billion-parameter roleplay and conversation model created by NeverSleep (IkariDev and Undi), built on the Llama 2 architecture. It supports a context window of up to 8,192 tokens. The model was trained on a mix of curated datasets, including the no_robots dataset for more natural, human-like output and the Aesir private RP dataset contributed by the MinervaAI team. This combination aims to produce responses that feel less formulaic than typical merge-based community models. Noromaid 20B targets interactive roleplay, character simulation, and open-ended creative dialogue. Its larger parameter count compared to 7–13B alternatives gives it better coherence in longer exchanges, making it a reasonable mid-size option for developers building narrative or conversational applications.
Frequently Asked Questions
The NeverSleep API gives you access to models for AI chat. Through Puter.js, you can start using NeverSleep models instantly with zero setup or configuration.
Puter.js supports a variety of NeverSleep models, including Lumimaid v0.2 8B and Noromaid 20B. Find all AI models supported by Puter.js in the AI model list.
With the User-Pays model, users cover their own AI costs through their Puter account. This means you can build apps without worrying about infrastructure expenses.
Puter.js is a JavaScript library that provides access to AI, storage, and other cloud services directly from a single API. It handles authentication, infrastructure, and scaling so you can focus on building your app.
Yes — the NeverSleep API through Puter.js works with any JavaScript framework, Node.js, or plain HTML. Just include the library and start building. See the documentation for more details.