Cloudflare's Clef Ditches Text Generation for Pure Scoring — and Runs 4x Faster

New open decision models return probabilities instead of text, using a frozen Qwen prefill plus a tiny schema head to accelerate classification and routing in agent systems.

Cloudflare released a pair of open models this week that reject the generate-everything orthodoxy. Clef and Clef-flash return probabilities instead of text, according to @testingcatalog — they're decision models, not chat models. The architecture, as described by @marcopapa99, pairs a frozen Qwen prefill with a tiny schema head, a combination that makes Clef roughly four times faster than generating an answer in text.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia curae.

Pellentesque habitant morbi tristique senectus et netus et malesuada fames ac turpis egestas. Proin pharetra nonummy pede. Mauris et orci. Aenean nec lorem. In porttitor. Donec laoreet nonummy augue. Suspendisse dui purus, scelerisque at, vulputate vitae, pretium mattis, nunc. Mauris eget neque at sem venenatis eleifend. Ut nonummy. Fusce aliquet pede non pede. Suspendisse dapibus lorem pellentesque magna integer malesuada.

Unlock the full briefing

Get every story in today's briefing, the full archive, and the daily AI intelligence brief.

All stories today

Full archive

Daily brief