← EVENT LIBRARY / Foundation Models

Cloudflare opens Clef decision models for fast structured routing

Cloudflare released Clef and Clef-flash, Apache-2.0 decision models that return bounded typed outputs for routing and classification. They are Jev-API compatible, available as open weights and hosted on Workers AI. Clef adds image input and a 64k context window; author benchmarks report median latency of 209.3 ms for Clef and 38.8 ms for Clef-flash.

Availability: Apache-2.0 weights and Workers AI hosting

What this means for you

For agent teams, a small deterministic decision model can move routine routing out of a general LLM's hot path. The public weights and API compatibility make a one-day latency, calibration and abstention comparison practical.

Evidence & related material

Technical details & scores
Models Clef and Clef-flash
Availability Apache-2.0 weights and Workers AI hosting
Compatibility Jev API
Context 64k for Clef
Author Latency median 209.3 ms Clef; 38.8 ms Clef-flash
Modalities text and image classification
Technical impact 3
Engineering value 4
Adoption signal 3
Maturity 3
Verification cost 2
Risk 2