Together AI: Tev1 4B Experimental
together/tev1-4b-experimental
Try Tev1 4B Experimental 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: "together/tev1-4b-experimental"
}).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: "together/tev1-4b-experimental"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
Tev1 4B Experimental is an experimental decision model from Together AI, a supervised fine-tune of Qwen3.5-4B rather than a general-purpose chat model.
It takes a system instruction plus a JSON payload containing a state, a question, and 2 to 24 labeled options, and returns a single letter naming the chosen option. Together fine-tuned it on 37,840 examples covering language classification, policy decisions, routing, and research-paper categorization, using LoRA for about $17 in compute.
On Together's own development evaluation, it scored 88.0% (880 of 1,000) on the main decision set and 100% (300 of 300) on a policy-transfer set, with every output a valid single letter. Together describes it as inspired by Jev, a decision-model concept, while keeping Qwen's standard next-token head rather than a non-autoregressive runtime.
It suits structured classification and routing tasks, such as support-ticket triage or policy checks, rather than open-ended conversation.
Context Window 33K
tokens
Max Output 31K
tokens
Input Cost $0.04
per million tokens
Output Cost $0
per million tokens
Release Date Sep 23, 2026
Try Tev1 4B Experimental for free
Try Tev1 4B Experimental instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Frequently Asked Questions
You can access Tev1 4B Experimental by Together AI 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.
Tev1 4B Experimental 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.
Tev1 4B Experimental 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.
| Price per 1M tokens | |
|---|---|
| Input | $0.04 |
| Output | $0 |
Tev1 4B Experimental was created by Together AI and released on Sep 23, 2026.
Tev1 4B Experimental supports a context window of 33K tokens. For reference, that is roughly equivalent to 66 pages of text.
Tev1 4B Experimental can generate up to 31K tokens in a single response.
Yes — the Tev1 4B Experimental 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 Tev1 4B Experimental to your app for free
Developers can integrate Tev1 4B Experimental for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.