Announcing Our Partnership with Infron

August 19, 2026

On this page

About Infron Models Available Through Infron Get Started Looking Ahead Related

We're announcing our partnership with Infron, an inference routing platform that reaches more than 100 upstream providers. A single integration widens what Puter.js can serve across hundreds of models at once, still with no API keys, no accounts, and no server-side setup.

About Infron

Infron puts one API in front of 400+ models from 100+ providers, covering chat, embeddings, and search.

The part that matters for a platform like ours is redundancy. Popular open-weight models are hosted by many inference providers at once, and Infron often has 5 to 16 separate paths to the same model. When one provider degrades or goes down, requests move to another path instead of failing. Infron publishes a 99.99% uptime SLA and offers zero-data-retention configurations.

Models Available Through Infron

Here are some of the most recent models this integration brings to Puter.js, served through Infron.

Solar Pro 4: Upstage's agentic model for multi-step work that spans documents, terminals, and tool calls
GLM 5.2 Fast: The high-throughput serving tier of Z.ai's GLM-5.2, for agent loops where latency matters more than cost
Kimi K2.7 Code Fast: Moonshot's coding-agent model on a faster serving route

Browse all models on Puter →

Get Started

All of these models are ready to use right now through Puter.js. Add one script tag to your HTML:

<script src="https://js.puter.com/v2/"></script>

Or install via npm:

// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

Then call any of them with a few lines of code:

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        // Chat with Solar Pro 4
        puter.ai.chat(`Hello, how are you?`, {
            model: 'upstage/solar-pro-4',
        }).then(puter.print);
    </script>
</body>
</html>

That's it. No API keys and no infrastructure setup.

Looking Ahead

We'd like to thank the Infron team for their collaboration and support in making this integration possible. We're glad to partner with a team working on the same problem we are, which is getting developers to a model without making them wire up infrastructure first.

Stay tuned for more updates as we continue to expand what's possible with Puter.js and Infron.

Ship a Full-Stack App with One Prompt

Give this to your AI Build an AI chat app using Puter.js

Try in

Coding manually? see the guide