Cloudflare introduces Clef-omni and says Clef is up to 2x faster
🎧 Listen to this story
Cloudflare has launched Clef-omni, an open-weight decision model that can process audio, video, images and text in a single pipeline or API call. The company says this removes the need for separate pipelines to transcribe audio or split video channels; the model accepts WAV and MP3 files, as well as MP4 and WebM, and its open weights are available on Hugging Face.
Cloudflare also cut the price of Clef-flash and says it has increased Clef inference speeds by up to 2x. Clef-omni is built on Qwen3-Omni-30B-A3B-Instruct, but uses its primary comprehension backbone without the text-to-speech output components, according to the company.
Why it matters · editorial interpretation
By handling audio, video, images and text in a single call, Clef-omni could reduce the integration complexity of multimodal applications. Its open weights on Hugging Face also allow developers to examine and adapt the model, while the reported speed gains and price cut may influence implementation choices, according to Cloudflare.