Clef Flash
cloudflare/clef-flash
Back to model catalog

Cloudflare · Model guide

Clef Flash

Compare
cloudflare/clef-flashReleased Oct 1, 2026

The smaller, faster variant of Cloudflare's Clef decision model. Same typed questions and probabilities, called through /v1/systemone or /v1/decisions. Best kept to short inputs: in our tests it stopped finding a planted fact once the input reached a few hundred tokens, at the start or the end alike, and the whole input is counted as input tokens either way.

Modalities
TextImageDecision
Context
66K
Max output
—
Price / 1M tokens
$ 0.090input only
Decision modelYes / noSingle choiceGraded scoreImage input

Returns probabilities, not text. Call it through /v1/decisions or /v1/systemone.

What this model is good at

What the vendor positions it for, and which of our models to reach for instead.

Best for
  • Short-input decisions at volume · A small model for one-line or one-paragraph inputs.

Neighbouring models
  • cloudflare/clefstronger —Use Clef for anything longer than a short paragraph.
Compare them side by side →

Pricing and billing

Billed on input tokens only. There is no output or cache price.

Input sizeInput / 1M tokens
Any size$ 0.090

The whole input counts, including question text and option descriptions. Output tokens, where the upstream reports them, are not charged.

What it answers

A decision model takes one shared input and a set of typed questions, and returns a probability for each.

Context window
65.5K tokens
Max output
—
Input / output modalities
Text + Image → Decision
Question types
Yes / no · Single choice · Graded score
Output
Probabilities per question — no generated text
Streaming
Not applicable — one response per call
Image input
Supported
Endpoints
/v1/decisions · /v1/systemone

Frequently asked questions

What is Clef Flash?
Clef Flash is a decision model, available on CrossModel as cloudflare/clef-flash. Instead of generating text it answers a set of typed questions about one shared input — yes/no, single choice, graded score — with a probability for each. Its context window is 66K tokens.
How much does Clef Flash cost?
Currently $ 0.090 per 1M input tokens. Decision models are billed on input only — there is no output price.
What kinds of questions can Clef Flash answer?
Three: yes/no predicates (a probability), single choice (a probability per option) and graded scores (a probability per level). It accepts images as part of the input.
Which endpoint do I call?
Call POST /v1/decisions (the OpenAI decisions shape) or POST /v1/systemone (the System One shape). Either works for every decision model. The chat endpoints do not accept decision models.
Can I try it without writing code?
Yes. Sign in and open the Playground on this page: fill in an input and a few questions and see the probabilities — no API key needed. Usage is billed from your wallet at the normal rate.

Try it on your own input

Fill in an input and a few questions in the Playground and see the probabilities, then wire it in.