Cloudflare released Clef-omni, an open-weight decision model that accepts audio, video, image, and text input, built on a Qwen3 Omni 30B A3B Instruct mixture-of-experts foundation1. The model scores a 21-second video clip with sound in approximately 1.5 seconds and processes text-only inputs at roughly 130 ms median latency. Clef-omni is priced at $0.15 per million input tokens, while Clef-flash dropped from $0.09 to $0.038 per million input tokens, which Cloudflare says makes it cheaper than TypeSafe AI's Jev. Weights are available on Hugging Face.
Cloudflare Ships Clef-omni, Adding Audio and Video to Its Decision Models
Cloudflare released Clef-omni, an open-weight multimodal decision model accepting audio, video, image, and text, priced at $0.15 per million input tokens.