Turn any state into a decision — in one pass
Clef-Flash is a 9B multimodal decision model. Give it a situation and a schema of typed questions; it returns a probability for every allowed answer. No chat, no prompt engineering, around 39 ms median.
Community-hosted demo of the 9B model. Runs live in your browser session.
How a decision model works
Three steps, one request. If your prompt ends with “answer with one of these options”, this is the model that was built for it.
Describe the state
Paste a support ticket, a JSON payload, a product description or an image reference. The state is the situation the model has to reason about — up to 64k tokens.
List the answers you allow
Write typed questions, each with a closed set of options. The schema is the contract: the model cannot answer outside it, so there is nothing to parse and no way for it to improvise.
Read the distribution
Every question comes back with a probability per option and a winning answer. Threshold on confidence, log the rest, and stop writing regexes against generated prose.
Decision model vs LLM
Same input, different contract. This is the distinction that decides your architecture.
| Large language model | Clef-Flash | |
|---|---|---|
| Output | Free text you have to parse | A probability per allowed option |
| Shape | Open-ended; the format drifts | Closed set, guaranteed by the schema |
| Cost of a mistake | A broken parser in production | A low confidence score you can threshold on |
| Best at | Writing, explaining, extracting | Routing, labelling, scoring, moderating |
What people use it for
Anywhere a system has to choose between bounded options before a human sees the queue.
Agent tool routing
Pick the next tool from a fixed catalogue before the agent spends a token on deliberation.
Support triage
Label intent and urgency, then route on the confidence score rather than on a guess.
Content moderation
Return a category and a probability you can defend after the fact.
Image labelling
The vision encoder takes an image as the state, so the same schema works for pictures.
Lead scoring
Bounded bands instead of a number a language model invented this time.
Quality gates
Approve, reject or escalate — with the distribution logged for review.
The facts, before the pitch
- Two models: Clef 27B for precision, Clef-Flash 9B for latency. Both Apache 2.0 with open weights.
- Clef-Flash is post-trained from Qwen3.5-9B with a vision encoder and a 64k context window.
- Published latency for Clef-Flash is about 39 ms median and 122 ms at p95 — over ten times faster than Jev on comparable tasks.
- Local inference needs roughly 41 GB of GPU VRAM for Clef-Flash and about 85 GB for the 27B Clef model. Both are on Ollama.
- Available on Cloudflare Workers AI, Ollama, Hugging Face and OpenRouter.
Questions people ask first
Is this site Cloudflare?
No. It is an independent playground. Clef and Clef-Flash are open-source models from Cloudflare, released under the Apache 2.0 licence, and this site is not affiliated with them.
What is the difference between Clef and Clef-Flash?
Clef is the 27B precision model; Clef-Flash is the 9B latency model. Start with Clef-Flash, and move only the questions it gets wrong to the larger model.
Do I need an account to try it?
No. The browser playground works without signing up. An API key only raises the daily decision quota.
Do you store the text I paste?
We store the count, the model and the latency — not the state itself. The privacy policy lists exactly what is kept.
Guides for builders
What Is a Decision Model? Typed Probabilities Instead of Chat
A decision model takes a state and a schema of typed questions and returns a probability for every allowed option in one pass — no chat, no prose.
Clef-Flash Benchmarks: Latency, Cost and Memory Explained
Clef-Flash is reported at roughly 39 ms median latency, 122 ms p95 and $0.09 per million input tokens — here is what each published figure actually means.
How to Run Clef-Flash on Ollama
Clef-Flash ships as an Ollama model: pull it, write a schema of typed questions and read a probability for every allowed option without leaving your machine.
Open the playground
Run a state through Clef-Flash right now. Nothing to install, no account needed.
Model notes
One short email when a new decision model lands or a benchmark changes. No spam, unsubscribe in one click.