# Cloudflare: clef

> Cloudflare's open-weight 27B multimodal decision model, post-trained from Qwen3.8-27B. A joint schema head scores every option of every noul, choice and score question in one prefill-only pass over text, JSON, images or video. Also hosted on Workers AI.

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

## Facts

| | |
|---|---|
| Maker | Cloudflare (https://systemonemodels.ai/cloudflare) |
| Decides | choice, score, noul |
| Architecture | clef |
| Base model | qwen/qwen3.8-27b |
| Parameters | 27B |
| Context | 64K tokens |
| Licence | apache-2.0 |
| Availability | Open weights + hosted API |
| Released | 2026-09-30 |
| Latest version | 2026.09 |

## Hosted API

- Provider: Cloudflare Workers AI (https://developers.cloudflare.com/workers-ai/models/clef/)
- Docs: https://developers.cloudflare.com/changelog/post/2026-10-01-clef-workers-ai/
- Input: $0.24/MTok · Output: —

## Reported evaluation

Suite: Decision Index 0.2.1 suite, Cloudflare's own run (41 benchmarks). Numbers are the publisher's own.

- Median latency: 209 ms
- p95 latency: 239 ms

## Model card

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

# Clef

Cloudflare's open-weight 27B multimodal decision model, post-trained from Qwen3.8-27B. A joint schema head scores every option of every noul, choice and score question in one prefill-only pass over text, JSON, images or video. Also hosted on Workers AI.

Clef returns one logit per allowed option (softmax per question); nothing is generated. It needs the repo's own joint_schema_model.py, which also exposes a Jev/SystemOne-style `systemone()` call. The hosted context is 65,536 tokens; the local code defaults to 16,384. Cloudflare's blog says training used a Brier loss, but no calibration figure is published. Sibling: Clef-flash (Cloudflare/clef-flash, 9B on Qwen3.5-9B; 38.8 ms median and 122.4 ms p95 request latency in Cloudflare's run; $0.09 per million input tokens on Workers AI). Cloudflare's own run of the community Decision Index 0.2.1 suite (a third-party board) gives Clef 61.21 and Clef-flash 57.07 on 36 of 38 panel benchmarks; these are self-reported, not the board's own measurement. Third-party quantisations exist and are not the maker's.

## 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 probability

## At a glance

| | |
|---|---|
| Parameters | 27B |
| Base model | `Qwen/Qwen3.8-27B` |
| Maker | Cloudflare |
| Released | 2026-09-30 |
| License | apache-2.0 |
| Reported latency | 209.3 ms p50 / 238.6 ms p95 request latency (hardware not stated; the card was tested on one H200) |

## Hosted API

Served by **Cloudflare Workers AI** — $0.24/MTok input. [Get access](https://developers.cloudflare.com/workers-ai/models/clef/) · [API docs](https://developers.cloudflare.com/changelog/post/2026-10-01-clef-workers-ai/).

## Get the weights

```bash
pip install systemonemodels
systemone pull cloudflare/clef
```

The files are served from the maker's Hugging Face repository, [`Cloudflare/clef`](https://huggingface.co/Cloudflare/clef), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/Cloudflare/clef)
- [Clef-flash (9B sibling)](https://huggingface.co/Cloudflare/clef-flash)
- [Announcement](https://blog.cloudflare.com/clef-decision-models/)
- [Workers AI changelog](https://developers.cloudflare.com/changelog/post/2026-10-01-clef-workers-ai/)
- [Workers AI (Clef-flash)](https://developers.cloudflare.com/workers-ai/models/clef-flash/)

---

*This page was opened by System One for Cloudflare, 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