Structured decision outputs
Takes a state and a schema of typed questions, then returns a probability for every allowed option of every question.
Loading page…
Productivity / product dossier
A 27B multimodal model that returns probabilities for typed decisions without generating text.
Product brief
Clef is a 27B multimodal model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, or video, and returns a probability for every allowed option of every question in a single forward pass. There is no free-form text generation and no output parsing. The Clef API is fully compatible with Jev and SystemOne.
Why we selected it
A technically distinct alternative to using text-generating models for structured decisions: typed questions receive option probabilities in one forward pass, without output parsing. Supports multimodal inputs and opens,
Product preview saved with our daily selection
Capability scan
Only capabilities supported by the product information we collected are listed here.
Takes a state and a schema of typed questions, then returns a probability for every allowed option of every question.
Reads state supplied as text, JSON, images, or video.
Returns all option probabilities in a single forward pass, without free-form text generation or output parsing.
The Clef API is fully compatible with Jev and SystemOne.
Best-fit use cases
FAQ
Clef is an open-source, 27B multimodal decision model from Cloudflare. It turns a state and a schema of typed questions into option probabilities.
Clef reads state as text, JSON, images, or video, alongside a schema defining the typed questions and allowed options.
No. It returns a probability for every allowed option of every question in a single forward pass, with no output parsing.
The Clef API is fully compatible with Jev and SystemOne.