Together AI · DECISION MODEL

Tev1 4B Experimental

An experimental Qwen-based decision model from Together AI that follows the Jev-style structured contract.

togethercomputer/tev1-4b-experimentalchoicescorenoul

Try this model Back to models

MODEL PROFILE

Together AI

MODEL ID

togethercomputer/tev1-4b-experimental

STRUCTURED OUTPUT

choice

score

noul

Its Choice output is designed for a bounded list of options, making it easy to evaluate side by side.

01 / Workbench

Decision workbench

Choose a task, edit the input, define typed questions, and preview the request before you connect the same workflow to your backend.

Unlimited free use in the online playground.

Workbench

Example library

What do you want to decide?

Choose a scenario to load editable input and rules. Loading an example uses no credits.

Examples load into the current draft only; no configurations or run history are saved.

ModelInput format

State

Give the selected model the context shared by every question.

Text

Input state

All questions share this context and are answered independently.

Questions

Define up to eight typed questions for the same state.

3 / 8

3. Run decision

Run the decision request.

Result preview

Subject: Charged twice again!! Hi — this is the SECOND month in a row I've been billed twice for the Pro plan. I already emailed last month and nobody replied. I run my whole business on this. If it's not refunded today I'm cancelling and disputing the charge with my bank.

↓One input → multiple structured decisions

Click “Generate decisions” to see typed output with probabilities.

Results are returned in a structured format so you can connect them to your application logic.

WHERE IT FITS

A model page for a clear decision boundary.

Its Choice output is designed for a bounded list of options, making it easy to evaluate side by side.

Choice experiments

Define the question, receive a typed signal, and connect the result to the next step in your workflow.

Model comparisons

Define the question, receive a typed signal, and connect the result to the next step in your workflow.

Lightweight routing

Define the question, receive a typed signal, and connect the result to the next step in your workflow.

ONE CONTRACT

Use the same decision shape in production.

The model changes, but your integration can keep a state, typed questions, and a predictable response contract.

Read the API docs

REQUEST EXAMPLE

POST /v1/systemone

{
  "model": "togethercomputer/tev1-4b-experimental",
  "state": "A customer reports a duplicate charge and needs a fast resolution.",
  "questions": {
    "route": {
      "type": "choice",
      "criteria": {
        "billing": "send to billing support",
        "account": "send to account support",
        "urgent": "escalate for immediate review"
      }
    },
    "urgent": {
      "type": "noul",
      "instructions": "Does this request need attention now?"
    }
  }
}