#Cloudflare
2 published articles
Cloudflare Clef and Clef-flash: Apache 2.0 multimodal decision models on Workers AI, with a 64k context window
The 27B and 9B models return probabilities for typed questions in one pass. Cloudflare prices Clef at $0.24 per million input tokens and says median latency is 209 ms.
Cloudflare puts Python Workers into general availability on 21 September
The release adds native Cloudflare bindings plus FastAPI, Django and Flask adapters to the Pyodide-based Workers runtime.