{"version":1,"type":"story","url":"https://digestai.news/story/cloudflare-releases-clef-omni-a-30b-multimodal-decision-model-for-text","json":"https://digestai.news/story/cloudflare-releases-clef-omni-a-30b-multimodal-decision-model-for-text.json","markdown":"https://digestai.news/story/cloudflare-releases-clef-omni-a-30b-multimodal-decision-model-for-text.md","slug":"cloudflare-releases-clef-omni-a-30b-multimodal-decision-model-for-text","headline":"Cloudflare releases Clef-omni, a 30B multimodal decision model for text, image, audio and video","summary":"Cloudflare launched Clef-omni on October 9, 2026, a new open-weight multimodal decision model that processes text, images, audio and video in a single call. Built on the Qwen3-Omni-30B-A3B-Instruct backbone, Clef-omni uses a mixture-of-experts (MoE) architecture with 3 billion active parameters and a 64,000-token context window on Workers AI. It supports up to four images, four audio clips, and two video clips per request, with latency of about 130 ms for text, 150 ms for images, and 1.5 seconds for 21-second videos with sound.\n\nCloudflare claims Clef-omni excels in intent classification, achieving a 97.7 macro-F1 score on CLINC150+OOS, but trails its own text-focused Clef model on reasoning and workflow tasks. The model’s pricing starts at $0.15 per million tokens, while Clef-flash pricing dropped to $0.038, now under TypeSafe’s Jev model. Cloudflare also improved hosted Clef performance by 1.7x to 2.0x using SGLang, with no new weights released.","keyPoints":["Clef-omni processes text, images, audio and video in one decision call, using a 30B MoE model with 64k context","Cloudflare claims 97.7 macro-F1 on CLINC150+OOS but lags behind Clef on reasoning and workflow benchmarks","Hosted Clef is now 1.7x–2.0x faster, Clef-flash costs $0.038, and Clef-omni is open-weight under Apache-2.0"],"whyItMatters":"A unified multimodal decision model could simplify pipelines for apps needing text, audio, video, and image analysis in one API call, reducing latency and complexity for developers.","category":{"slug":"models","name":"Generative AI & Models","url":"https://digestai.news/category/models"},"entities":{"companies":["Cloudflare","TypeSafe"],"models":["Clef-omni","Clef","Clef-flash","Jev","Qwen3-Omni-30B-A3B-Instruct"],"people":[]},"firstPublishedAt":"2026-10-11T23:15:52Z","updatedAt":"2026-10-11T23:15:52Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"MarkTechPost","title":"Meet Cloudflare Clef-omni: A 30B-A3B Multimodal Decision Model for Audio, Video, Image and Text","url":"https://marktechpost.com/2026/10/11/cloudflare-clef-omni-multimodal-decision-model","publishedAt":"2026-10-11T23:15:52Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":{"title":"Cloudflare Expands Agent Infrastructure Ecosystem","url":"https://digestai.news/thread/cloudflare-launches-cf-cli-to-let-agents-use-its-full-api","storyCount":3},"cite":{"text":"Digest AI, \"Cloudflare releases Clef-omni, a 30B multimodal decision model for text, image, audio and video\", 11 October 2026, https://digestai.news/story/cloudflare-releases-clef-omni-a-30b-multimodal-decision-model-for-text","publisher":"Digest AI","title":"Cloudflare releases Clef-omni, a 30B multimodal decision model for text, image, audio and video","datePublished":"2026-10-11T23:15:52Z","url":"https://digestai.news/story/cloudflare-releases-clef-omni-a-30b-multimodal-decision-model-for-text"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}