# vLLM Semantic Router: decision

> The flagship of the vLLM Semantic Router team's Decision 1.0 family. Qwen3.5-9B with a shared candidate head returns a probability for every supplied answer to choice, yes/no and score questions, over a 16,384-token input.

- Page: https://systemonemodels.tech/vllm-semantic-router/decision
- API: https://api.systemonemodels.tech/v1/models/vllm-semantic-router/decision
- Download: `pip install systemonemodels && systemone pull vllm-semantic-router/decision`

## Facts

| | |
|---|---|
| Maker | vLLM Semantic Router (https://systemonemodels.tech/vllm-semantic-router) |
| Decides | choice, score, noul, classify, route |
| Architecture | decision |
| Base model | qwen/qwen3.5-9b |
| Parameters | 9.0B |
| Context | 16K tokens |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-22 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted). Numbers are the publisher's own.

- Decision accuracy: 77.4%

## Model card

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

# Decision-1.0-Lux-9B

The flagship of the vLLM Semantic Router team's Decision 1.0 family. Qwen3.5-9B with a shared candidate head returns a probability for every supplied answer to choice, yes/no and score questions, over a 16,384-token input.

On the team's 54-task benchmark (3,766 decisions, weighted across general decisions, composition, reading, inference and transfer) Lux-9B scores 77.40%, against 81.05% for Jev and 71.89% for Kev-9B on the same benchmark. Choice takes 2 to 255 options and score 2 to 10 levels. The repository holds the fine-tuned backbone, the candidate head and fitted temperatures; serving runs through vLLM Semantic Router's Decision runtime, which speaks /v1/systemone. Siblings, all Apache-2.0: Nox-4B (73.09%), Sol-2B (66.32%) and Eos-0.8B (61.89%) on Qwen3.5, and Kai-0.6B (53.52%) and Lex-0.6B on the team's Vela encoder, which keep their upstream Gemma tokenizer terms.

## What it decides

- **choice** — picks one option from a set
- **score** — places the input on an ordered scale
- **noul** — answers a yes/no question with one calibrated probability
- **classify** — assigns a category from a fixed taxonomy
- **route** — sends the input to one of several destinations

## At a glance

| | |
|---|---|
| Parameters | 9B |
| Base model | `qwen/qwen3.5-9b` |
| Maker | vLLM Semantic Router |
| Released | 2026-09-22 |
| License | apache-2.0 |
| Reported accuracy | 77.4% |

## Get the weights

```bash
pip install systemonemodels
systemone pull vllm-semantic-router/decision
```

The files are served from the maker's Hugging Face repository, [`llm-semantic-router/Decision-1.0-Lux-9B`](https://huggingface.co/llm-semantic-router/Decision-1.0-Lux-9B), and verified against the checksums recorded here.

## Read more

- [Announcement](https://vllm-sr.ai/blog/decision-models/)
- [Runtime](https://github.com/vllm-project/semantic-router)
- [Weights on Hugging Face](https://huggingface.co/llm-semantic-router/Decision-1.0-Lux-9B)
- [Decision-1.0-Nox-4B](https://huggingface.co/llm-semantic-router/Decision-1.0-Nox-4B)
- [Decision-1.0-Kai-0.6B](https://huggingface.co/llm-semantic-router/Decision-1.0-Kai-0.6B)

---

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

---

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