cloudflare
Cloudflare: Clef Omni
cloudflare/clef-omni
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
cloudflare/clef-omni is Cloudflare's mixture-of-experts Clef Omni decision model, post-trained from Qwen3-Omni-30B-A3B-Instruct and listed by OpenRouter as accepting text, image, audio, and video inputs while returning decisions. Cloudflare describes it as reading a state plus a typed question schema and scoring every allowed option jointly, rather than generating free-form text. The source pack includes publisher documentation and catalog data, but no third-party model card or independent evaluation; reported benchmark and workflow results should be treated as publisher-measured evidence and validated on target workloads.[1][2]
Strengths
- Accepts text or JSON state plus images, audio, and video, and returns probabilities for all options in a typed question schema.[1][2]
- Uses a 30B-total, 3B-active mixture-of-experts backbone with a joint schema head that scores related questions together.[1][2]
- Provides a Jev/SystemOne-compatible interface and an Apache-2.0 release with runnable Transformers examples.[2]
Limitations
- It is designed for typed decisions only: Cloudflare says there is no free-form text generation or output parsing, so it is not a general chat model.[2]
- Evidence is limited to an API catalog and publisher documentation; reported evaluations are internal rather than independent, and real workload validation remains necessary.[1][2]
- The documented local setup uses a single H200 with about 64 GB of GPU memory in bfloat16, while SGLang support is described as coming soon.[2]
Where to use it
- Evaluate for business triage or routing where each request must map to fixed choices, ordered scores, or true/false outcomes.[2]
- Consider for multimodal record review that combines a JSON or text state with attached images, audio, or video.[1][2]
- Potentially useful as a decision layer when downstream systems consume per-option probabilities directly rather than generated prose.[2]
Sources
- [1] OpenRouter catalog · Cloudflare: Clef OmniSources checked: Nov 13, 2026
- [2] Model documentation · Cloudflare: Clef OmniSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Clef Omni is the mixture-of-experts member of Cloudflare's open-source Clef decision model family, a fine-tune of Qwen3-Omni-30B-A3B (30B total, 3B active parameters) served on Workers AI. It turns a state...
Specifications
- Model ID
- cloudflare/clef-omni
- Canonical ID
- cloudflare/clef-omni-20261009
- Creator
- cloudflare
- Added to OpenRouter
- 09.10.2026
- Context length
- 65,536
- Modality
- text+image+audio+video->decisions
- Input modalities
- text, image, audio, video
- Output modalities
- decisions
- Token pricing
- No per-token price in the source snapshot — see OpenRouter for the billing unit
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | — |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | input: audio |
| Video | No measurement | input: video |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Cloudflare | 65,536 | — | — | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.