Ship a Full-Stack App with One Prompt

Copy this prompt into your AI coding agent, or open it in one below.

Give this to your AI Create a to-do list app using Puter.js

Coding manually? see the guide

TypeSafe

TypeSafe: Jev Router

typesafe/jev-router

Try Jev Router for free in your browser, and add it to your app for free with Puter.js AI API.

Try it free Add to your app
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

puter.ai.chat("Explain quantum computing in simple terms", {
    model: "typesafe/jev-router"
}).then(response => {
    document.body.innerHTML = response.message.content;
});
<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("Explain quantum computing in simple terms", {
            model: "typesafe/jev-router"
        }).then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>

Model Card

Jev Router is a model-routing endpoint from TypeSafe, built on Jev, the company's first System One decision model. Rather than generating the reply itself, Jev reads each request, scores it for difficulty and precision, and picks which underlying model and reasoning effort to use for that turn, balancing quality, speed, and cost.

The router is cache-aware: when it switches to a different underlying model mid-conversation, cached chat history carries over, so the new model does not need to reread the full conversation from scratch. It accepts text, image, video, audio, and PDF input and returns text.

Jev Router has a 1,000,000 token context window. On four agent benchmarks reported by OpenRouter, it solved 82% more tasks than OpenRouter's own Auto Router. It was added to OpenRouter on September 25, 2026.

Context Window 1M

tokens

Max Output 1M

tokens

Input Cost $1,000,000

per million tokens

Output Cost $1,000,000

per million tokens

Input text, image, video, audio, pdf

modalities

Release Date Sep 25, 2026

 

Try Jev Router for free

Try Jev Router instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.

Chat typesafe/jev-router
TypeSafe
Chat with Jev Router
Powered by Puter.js

Frequently Asked Questions

How do I use Jev Router?

You can access Jev Router by TypeSafe through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.

Can I try Jev Router for free?

Jev Router is free to try with a Puter account. Every account includes a free AI allowance, and you can chat with it in the playground on this page. You can upgrade your account anytime for a larger allowance.

Is the Jev Router API free for developers?

Jev Router is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.

What is the pricing for Jev Router?
Jev Router costs $1,000,000 per 1M input tokens and $1,000,000 per 1M output tokens.
Price per 1M tokens
Input$1,000,000
Output$1,000,000
Who created Jev Router?

Jev Router was created by TypeSafe and released on Sep 25, 2026.

What is the context window of Jev Router?

Jev Router supports a context window of 1M tokens. For reference, that is roughly equivalent to 2,000 pages of text.

What is the max output length of Jev Router?

Jev Router can generate up to 1M tokens in a single response.

What types of input can Jev Router process?

Jev Router accepts the following input types: text, image, video, audio, pdf. It produces: text.

Does it work with React / Vue / Vanilla JS / Node / etc.?

Yes — the Jev Router API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.

Add Jev Router to your app for free

Developers can integrate Jev Router for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.

Get started How pricing works