Cloudflare ships Clef-omni: full multimodal decision model with ~130ms median latency
dl_weekly · x · 2026-10-19
Cloudflare released Clef-omni, an open-weight decision model built on Qwen3-Omni-30B-A3B that accepts audio, video, image and text input and returns text decisions at 130ms median latency, removing cascading transcription/frame-extraction pipelines. It also made Clef faster and cut Clef-flash pricing below TypeSafe's Jev. The team says the original Clef went from Friday-evening idea to trained model and Thursday launch in under a week.
More from Infra
- GPU programmer says the field needs lighter, more predictable inference engines — brandon_xyzw · 2026-10-19
- llama-doctor: CLI that diagnoses your llama.cpp server from /metrics with severity-graded findings — msalsas · 2026-10-19
- Underwater AI data center planned in Alaska's Cook Inlet, home to 330 endangered belugas — anselm · 2026-10-19
- DeepInfra selling DeepSeek v4.1 at 49% off sparks doubts it can turn a profit — gharik · 2026-10-19
- 330MB EmbeddingGemma2 indexes 6,000+ screenshots: text beats visual descriptors in cosine similarity — jupiterbjy · 2026-10-19
- OpenFaaS bought 4x DGX Sparks for air-gapped coding and red-teaming — natesiggard · 2026-10-19