innFactory AI Consulting from Rosenheim adds Clef because Cloudflare extends the category of System One models we explained in Jev by TypeSafe: the AI model that writes no text with an open, multimodal and hosted offering. This page is based on the Cloudflare blog announcements for Clef and Clef-omni, the Workers AI changelog posts of 1 October and 9 October 2026, the model pages for Clef, Clef-omni and Clef-flash, the Workers AI price list and the model cards on Hugging Face. This overview reflects the state as of October 2026.
What is Clef?
On 1 October 2026 Cloudflare released Clef and Clef-flash, the first models the company has trained itself; Clef-omni followed on 9 October 2026. All three are decision models: they take a state (a support case, a web page, an agent trace, an image, a voice recording) plus a list of typed questions and return probabilities over predefined answers for each question. They generate no text. The question types are the same as with Jev: noul (yes/no as a probability), choice (one option from a list with a probability per option) and score (a level on a rubric). Cloudflare describes the models as fully compatible with the Jev API.
| Clef | Clef-omni | Clef-flash | |
|---|---|---|---|
| Workers AI ID | @cf/cloudflare/clef | @cf/cloudflare/clef-omni | @cf/cloudflare/clef-flash |
| Base | Qwen3.8-27B (frozen) with vision encoder | Qwen3-Omni-30B-A3B-Instruct with vision and audio encoders | Qwen3.5-9B (frozen) with vision encoder |
| Parameters | 27 billion | 30 billion, 3 billion active (MoE) | 9 billion |
| Inputs | text, JSON, images, video | text, JSON, images, audio, video with sound | text, JSON, images, video |
| Context (Workers AI) | 65,536 tokens | 64,000 tokens | 24,576 tokens |
| Price (Workers AI) | USD 0.24 per 1M input tokens | USD 0.15 per 1M input tokens | USD 0.038 per 1M input tokens |
| Median latency (Cloudflare, H200) | 209.3 ms | not in the comparison table | 38.8 ms |
| Licence | Apache 2.0 | Apache 2.0 | Apache 2.0 |
Technically, a joint schema head sits on top of the Qwen backbone: a small transformer that routes the evidence in the state to the questions and emits exactly one logit per option. Per the blog it was trained with label-smoothed cross-entropy, a Brier loss for calibration and Reinforcement Learning for Calibrated Decisions (RLCD) as a secondary target. The backbone stays frozen while low-rank adapters (LoRA) are trained; per Cloudflare, Clef-omni was trained with the same techniques.
Clef-omni: audio and video with sound
Clef-omni reads every modality in one request: text, JSON, images, audio (WAV or MP3) and video (MP4 or WebM). For videos the model evaluates the soundtrack together with the frames, so a decision can rest on what is seen and heard. Previously such a case needed a chain of transcription, track splitting and a text decision model. On Workers AI Clef-omni accepts up to 4 audio clips (8 MiB and 300 seconds each) and 2 videos (16 MiB and 60 seconds each); audio and video together may not exceed 16 MiB decoded. Billing runs through input tokens: audio about 780 tokens per minute, video up to about 15,400 tokens per minute at maximum resolution plus about 780 tokens per minute for the sound. Cloudflare gives different latency figures in the blog and in the changelog; before using it in latency-critical paths, measure it yourself.
Inputs and limits on Workers AI
- State: text, JSON objects or arrays, up to 4 images (PNG, JPEG, WebP, at most 4 MiB and 16 megapixels each) and video; Clef-omni additionally accepts audio. Request body for Clef and Clef-flash at most 13 MiB, decoded image data at most 8 MiB.
- Context: Clef 65,536 tokens, Clef-omni 64,000 tokens, Clef-flash 24,576 tokens. Images cost 64 to 1,024 input tokens depending on resolution; media tokens count toward the context, and an overly long text state is truncated.
- Questions: 1 to 64 per request, question IDs up to 100 characters.
- Response: model identifier,
answerskeyed like the questions, andusage. - Call: Workers binding
env.AI.run(), REST endpoint/ai/runor via the Cloudflare AI Gateway; examples for TypeScript, Python and cURL in the docs. - Billing: Workers AI bills in neurons (Clef 21,818, Clef-omni 13,636, Clef-flash 3,455 neurons per 1 million input tokens); 10,000 neurons per day are free, beyond that USD 0.011 per 1,000 neurons on the Workers Paid plan. Cloudflare does not charge for output tokens on Clef models.
On 9 October 2026 Cloudflare cut the price of Clef-flash from USD 0.09 to USD 0.038 per 1 million input tokens and in return reduced the hosted context from 64K to 24K tokens; per Cloudflare 0.24% of requests exceed this limit. Anyone checking longer states uses Clef. At the same time Cloudflare moved the hosted serving of Clef to SGLang.
Benchmarks: Cloudflare’s figures
Cloudflare publishes a table against Jev in the blog; per the changelog a Clef model leads on 7 of 10 decision benchmarks. These are vendor figures; the GPQA Diamond and MMLU-Pro values come from the model cards.
| Benchmark | Clef | Clef-omni | Clef-flash | Jev (per Cloudflare) |
|---|---|---|---|---|
| BFCL, case exact | 98.47 | 98.2 | 98.76 | 95.75 |
| ToolRet, nDCG@10 | 69.19 | 66.6 | 66.43 | 65.28 |
| API-Bank, accuracy | 91.93 | 92.7 | 93.11 | 88.19 |
| BANKING77, macro-F1 | 94.20 | 94.8 | 90.93 | 79.74 |
| CLINC150+OOS, macro-F1 | 97.43 | 97.7 | 66.77 | 89.27 |
| GPQA Diamond (knowledge) | 48.0 | 47.4 | 51.0 | 78.3 |
| MMLU-Pro (knowledge) | 65.9 | 70.6 | 65.3 | 82.7 |
Two things stand out. First, Jev leads clearly on the knowledge benchmarks, the Clef models on the tool and intent tasks. Second, Clef-flash collapses on CLINC150 with out-of-scope detection (66.77 versus 97.43 for Clef). Anyone picking Clef-flash for its latency or price should test out-of-scope cases separately.
In the workflow evaluations published by TypeSafe (invoice processing, customer service, security incidents) the models are close per Cloudflare: 64.7 / 60.2 / 57.1 / 61.8 on invoices, 76.3 / 71.6 / 77.0 / 76.0 in customer service, 62.9 / 61.7 / 61.7 / 61.7 on incidents (Clef / Clef-omni / Clef-flash / Jev).
Latency (Cloudflare measurement on an H200): Clef 209.3 ms median and 238.6 ms p95, Clef-flash 38.8 ms and 122.4 ms, Jev 524.1 ms and 536.0 ms. In the same table Cloudflare lists Laya at 5.8 ms median but 222.5 ms p95. For the hosted version of Clef after the serving optimisations, including the move to SGLang, Cloudflare states a median of 152 ms at about 800 tokens, 305 ms at about 3,400 tokens and 1,635 ms at about 16,000 tokens, 1.7 to 2 times the previous speed.
Independent single test: a developer compared Clef-flash locally on an RTX 3090 against the Jev API on 42 decisions of an autonomous agent: Jev 71.4%, Clef-flash 66.7%, the same decision in 83% of cases; identical on computer-use actions and supervision, 10 instead of 12 of 20 hits on triage. The test is small and not peer-reviewed, but it shows the order of magnitude. A practical note from it: community GGUF quantisations lack the decision head, PyTorch is needed for full functionality; Clef (27B) needs around 54 GB of GPU memory in BF16.
Data protection, regions and self-hosting
For the hosted variant Cloudflare states that requests and responses are neither read, stored nor used for training, unless the customer uses the fine-tuning offering. The Workers AI data usage docs confirm that customer content is not used to train models or improve services. Workers AI runs on Cloudflare’s global network; the Data Localization Suite documentation does not list Workers AI as a product with region pinning. Anyone who needs a contractual commitment to processing in the EU should clarify that with Cloudflare or take the second route.
The second route is self-hosting: the weights of all three models are on Hugging Face under Apache 2.0 (Cloudflare/clef, Cloudflare/clef-omni, Cloudflare/clef-flash). The model cards describe operation with Transformers and a systemone() function for the Jev-compatible interface; for Clef and Clef-flash SGLang is added, via a Docker image with a Jev-compatible endpoint /v1/systemone (per Cloudflare, support is due to land in the regular SGLang 0.5.22 release). For Clef-omni SGLang is announced. Cloudflare tested on a single H200 in BF16; per its model card Clef-omni needs around 64 GB of GPU memory. That lets you run the models on your own infrastructure or with an EU cloud provider, with full data control.
RL fine-tuning platform
Together with Clef, Cloudflare announced a platform for reinforcement learning fine-tuning. The building blocks: AI Gateway captures production data, Workers AI generates rollouts, Cloudflare Containers serve as the RL sandbox, a new Trainer updates the weights, and the result is redeployed via Workers AI with a bring-your-own model. At launch it is a guided offering with Cloudflare’s forward-deployed engineers via a design-partner form; a self-serve version is announced, pricing is not published.
Positioning: Clef, Jev and Laya
| Clef / Clef-omni / Clef-flash | Jev | Laya | |
|---|---|---|---|
| Licence | Apache 2.0, open weights | proprietary API | Apache 2.0, open weights |
| Operation | Workers AI or self-hosting | API only (US) | self-hosting only |
| Size | 27B / 30B-A3B / 9B (Qwen base) | not published | 0.3 to 0.4B (encoder) |
| Inputs | text, JSON, images, video; Clef-omni also audio | text, JSON | text, JSON |
| Context (hosted) | 65,536 / 64,000 / 24,576 tokens | 64,000 tokens combined | 512 to 1,024 tokens, windows up to 8,192 |
| Hosted price | USD 0.24 / 0.15 / 0.038 per 1M input | USD 0.042 per 1M input | no hosted API |
| EU residency | via self-hosting | not documented | via self-hosting |
Clef closes the gap between Jev (strong, but closed and US-hosted) and Laya (open, but small): open models with an LLM-sized backbone, image and video input, audio input with Clef-omni, and a hosted option with a price. Hosted Clef-flash is priced below Jev, Clef and Clef-omni above it; per Cloudflare the latency of Clef-flash is below that of Jev. None of the three replaces an LLM; for text, summaries and code, models such as Qwen, Mistral or GPT-OSS remain in charge.
Our recommendation
For companies in the DACH region Clef is interesting above all as a self-hosted decision model: open licence, Jev-compatible interface, image and video input, and with Clef-flash a variant that runs on a single GPU. For decisions on voice recordings or videos with sound, for example in quality control or on call recordings, Clef-omni is the fitting variant. Hosted, Clef-flash is the cheapest of the three at USD 0.038 per 1 million input tokens, but limited to a 24,576-token context. Check three points before adopting it: out-of-scope detection with Clef-flash, language quality on German data (Cloudflare publishes English benchmarks only) and, for hosted operation, the contractual situation regarding the processing region. We assess its use as a front stage to language models in CompanyGPT or as a router in the AI Gateway per project. For an assessment of whether a decision model fits your architecture, contact innFactory AI Consulting.
Related decision models
The decision model (System One) category also includes Microsoft-Decision-1.1, Gemini Decision 1, Laya, Jev, Julia-1, GLiNER2.5-Decide. OpenAI is moving in the same direction with the Decisions API based on GPT-6 Luna; details are on the OpenAI GPT page.
