# Together AI: tev1

> Together AI's Jev-style classifier. A LoRA fine-tune of Qwen3.5-4B that reads a state, a question and 2 to 24 options and returns one option letter. Served on Together's platform; recipe published.

- Page: https://systemonemodels.ai/together-ai/tev1
- API: https://api.systemonemodels.ai/v1/models/together-ai/tev1
- Download: `pip install systemonemodels && systemone pull together-ai/tev1`

## Facts

| | |
|---|---|
| Maker | Together AI (https://systemonemodels.ai/together-ai) |
| Decides | choice, classify, route |
| Architecture | tev |
| Base model | qwen/qwen3.5-4b |
| Parameters | 4.0B |
| Licence | Unspecified — weights licence being finalised |
| Availability | Open weights + hosted API |
| Released | 2026-09-23 |
| Latest version | 2026.09 |

## Hosted API

- Provider: Together AI (https://api.together.ai/models/together/Tev1-4B-experimental)

- Input: $0.042/MTok · Output: Free

## Reported evaluation

Suite: Together development set (reused, not held out). Numbers are the publisher's own.

- Decision accuracy: 88.0%

## Model card

<!-- generated by scripts/seed_catalog.py; edit content/models/catalog.yaml -->

# Tev1-4B-experimental

Together AI's Jev-style classifier. A LoRA fine-tune of Qwen3.5-4B that reads a state, a question and 2 to 24 options and returns one option letter. Served on Together's platform; recipe published.

Tev1 keeps the language-model head and answers by emitting a single option letter, so it is Jev-inspired rather than a non-autoregressive decision head. Together reports 880 of 1,000 on a development set and 300 of 300 on a policy-transfer check; the development set was reused rather than held out, and the authors say the log-probabilities are not calibrated. The weights sit on Hugging Face without a licence field while their licence is finalised, so this registry links to them and does not mirror them. The training code is MIT. A Tev1-0.8B-experimental on Qwen3.5-0.8B followed on 25 September, also without a licence field while its licence is finalised.

## What it decides

- **choice** — picks one option from a set
- **classify** — assigns a category from a fixed taxonomy
- **route** — sends the input to one of several destinations

## At a glance

| | |
|---|---|
| Parameters | 4B |
| Base model | `qwen/qwen3.5-4b` |
| Maker | Together AI |
| Released | 2026-09-23 |
| License | Unspecified — weights licence being finalised |
| Reported accuracy | 88.0% |

## Hosted API

Served by **Together AI** — $0.042/MTok input, $0/MTok output. [Get access](https://api.together.ai/models/together/Tev1-4B-experimental).

## Get the weights

```bash
pip install systemonemodels
systemone pull together-ai/tev1
```

The files are served from the maker's Hugging Face repository, [`togethercomputer/Tev1-4B-experimental`](https://huggingface.co/togethercomputer/Tev1-4B-experimental), and verified against the checksums recorded here.

## Read more

- [Weights on Hugging Face](https://huggingface.co/togethercomputer/Tev1-4B-experimental)
- [On Together AI](https://api.together.ai/models/together/Tev1-4B-experimental)
- [Tev1-0.8B-experimental](https://huggingface.co/togethercomputer/Tev1-0.8B-experimental)

---

*This page was opened by System One for Together AI, who can claim the organisation and take it over at any time.*

---

From System One Models — https://systemonemodels.ai/ · every System One model: https://systemonemodels.ai/system-one-models