Cloudflare Clef-omni: decisions from photo, audio, and video
Why it matters
Open-weight multimodal decision model takes audio, video, image and text in one call; Cloudflare reports ~130 ms text / ~1.5 s for a 21s video+sound.
Read the source: Cloudflare (opens in a new tab)
All hits from 13 Oct 2026More VisionGet the daily hits by email