Loveon API
Access Loveon 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: "loveon/loveon_l"
}).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: "loveon/loveon_l"
}).then(response => {
console.log(response);
});
</script>
</body>
</html>
List of Loveon Models
Loveon L
loveon/loveon_l
Loveon L is a chat model from Infron, built to power the Loveon AI companion app, and is designed for emotionally rich conversations and romantic roleplay scenarios. It sits in Infron's lineup of models optimized for character-driven, immersive roleplay rather than general assistant work, with an emphasis on keeping a persona's tone and emotional register consistent through a conversation. The model has a context window of just over 1 million tokens, enough to hold long chat histories and detailed character backstories without losing earlier turns, and a maximum output of 65,535 tokens per response. An upgraded L2 variant exists in the same series with improved memory and character consistency, making Loveon L the earlier baseline model. It fits developers building AI companion, girlfriend/boyfriend, or character-chat products who want a model tuned for sustained romantic and emotional dialogue rather than factual or technical tasks.
ChatLoveon L2
loveon/loveon_l2
Loveon L2 is Infron's upgraded model in the Loveon series, built for the Loveon AI companion app and geared toward emotionally rich, romantic roleplay conversations. Compared to the original Loveon L, Infron describes L2 as offering more nuanced emotional expression along with improvements to long-conversation memory and character consistency, so a persona's personality and backstory hold up over extended chats instead of drifting. Like Loveon L, it has a context window of just over 1 million tokens and a maximum output of 65,535 tokens per response, enough to carry long roleplay sessions and detailed character sheets without truncating chat history. It targets developers building AI companion, girlfriend/boyfriend, or character-roleplay chat products who want a model tuned specifically for sustained, emotionally consistent dialogue rather than general-purpose assistant work.
ChatLoveon S
loveon/loveon_s
Loveon S is a chat model from Infron in the same Loveon series as Loveon L and Loveon L2, built to power the Loveon AI companion and roleplay chat app. Infron publishes marketing material describing what Loveon L and L2 improve on, but we found no equivalent description of Loveon S's design goals, training, or intended improvements, so we can't characterize it beyond its place in the lineup. It has a much smaller context window (100,000 tokens) and lower max output (20,000 tokens) than the L-series models, and it's priced well below them per token, which points to it being a lighter, cheaper option rather than the flagship model. Developers who need a lower-cost companion or roleplay chat model for shorter conversations, and don't need the multi-hundred-thousand-token context of Loveon L or L2, may find Loveon S a cheaper fit for their use case.
Frequently Asked Questions
The Loveon API gives you access to models for AI chat. Through Puter.js, you can start using Loveon models instantly with zero setup or configuration.
Puter.js supports a variety of Loveon models, including Loveon L, Loveon L2, and Loveon S. 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 Loveon 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.