From the source
Cloudflare released Clef-omni, a new open-weight decision model that accepts audio, video, image, and text input natively, built on a Qwen3-Omni-30B-A3B-Instruct MoE foundation.
The company also reduced the price of Clef-flash from $0.09 to $0.038 per million input tokens, making it cheaper than Jev, and made Clef faster.
Text-only decisions return in about 130 ms median, image inputs in about 150 ms, and a full 21-second video clip with sound in about 1.5 seconds.
