A Cloudflare megjelentette a Clef döntési modellcsalád legújabb nyílt tagját, a Clef-omni-t. Az eszköz a generált szöveg helyett valószínűségeket és strukturált válaszokat ad vissza. A modell egyetlen kéréssel dolgozza fel a szöveget, képeket, hanganyagokat és videókat, így nincs szükség külön átírási vagy feliratozási lépésekre. A teljes infrastruktúrát átültették SGLang alapperemre is, ami duplájára gyorsította a válaszidőket.
A Qwen3-Omni-30B-A3B modellre épülő rendszer 30 milliárd teljes és 3 milliárd aktív paraméterrel működik. A Workers AI platformon 64 000 tokenes kontextust támogat, de a nyílt licencnek köszönhetően saját szerveren (például egyetlen H200-as GPU-n) is futtatható. A tesztek alapján a szándékfelismerési feladatokban kifejezetten erős, míg az összetettebb logikai érvelésben kissé elmarad a csak szöveges változatok mögött.
A Clef-omni használati díja 0,15 dollár 1 millió bemeneti tokenenként a Workers AI-on. Ezzel párhuzamosan a kisebb Clef-flash árát 0,038 dollárra csökkentették, a modell súlyai pedig elérhetők az Apache-2.0 licenc alatt.
Az eredeti szöveg (MarkTechPost)
Cloudflare has released Clef-omni , a new open-weight member of its Clef decision model family. Clef-omni is a Cloudflare decision model that scores text, images, audio and video in 1 call. It arrived on October 9, 2026, 8 days after the original Clef and Clef-flash launch . The same update cut Clef-flash pricing below TypeSafe’s Jev and made hosted Clef roughly 2x faster. For developers, this removes the transcription and captioning steps that multimodal agent pipelines usually need.
TL;DR
Size: 30B total, 3B active parameters (MoE); 64,000-token context on Workers AI
Runs on: Workers AI as @cf/cloudflare/clef-omni ; self-hosting tested on a single H200, about 64 GB GPU memory in bfloat16
Performance: Close to Clef on routing and intent tasks, behind it on most reasoning and workflow evals
Best: 97.7 macro-F1 on CLINC150+OOS, top of the 4 Clef and Jev models
Worst: 2.6 accuracy on POP909-CL, and 47.4 on GPQA Diamond versus Jev’s 78.3
Bottom line:
Best: one call decides across 4 modalities.
Worst: weaker accuracy than text-focused Clef on hard reasoning.
What is a decision model?
A decision model returns typed answers with probabilities instead of generated text. You send a state and a schema of questions. The model returns a probability for every allowed option. Clef supports 3 question types : noul (true or false), choice and score . The format follows the Jev and SystemOne API from TypeSafe AI .
How does Clef-omni work?
Clef-omni is post-trained from Qwen3-Omni-30B-A3B-Instruct . Cloudflare keeps the comprehension backbone and drops the text-to-speech output path. The model runs a single prefill pass over the full payload. Video frames and audio are synced into 1 sequence for joint processing.
A small joint schema head then scores the options. Each valid option first gathers evidence from the input. Field vectors then cross-attend across the full context to compute confidence scores. Cloudflare froze the Qwen3 backbone and trained LoRA adapters. Training combined label-smoothed cross-entropy with Brier score calibration.
Supported inputs on Workers AI, per the developer docs :
Images: up to 4, PNG, JPEG or WebP, 64 to 1,024 tokens each
Audio: up to 4 clips, WAV or MP3, 300 seconds each, about 780 tokens per minute
Video: up to 2 clips, MP4 or WebM, 60 seconds each, sampled at 2 frames per second
Questions: 1 to 64 per request
Cloudflare reports text decisions in about 130 ms at the median and images in about 150 ms. A 21-second video with sound scores in about 1.5 seconds.
How does Clef-omni perform on benchmarks?
Cloudflare compared Clef-omni against Clef, Clef-flash and Jev on its Decision Index run. Clef-omni leads on intent classification: 94.8 macro-F1 on BANKING77 and 97.7 on CLINC150+OOS. It also tops Amazon ESCI at 57.8.
It trails elsewhere. Home appliances case-exact accuracy is 69.3, versus 97.73 for Clef-flash. When2Call accuracy is 63.3, versus 80.97 for Jev. On TypeSafe’s workflow evals , Clef-omni scores below Clef in all 5 reported metrics.
Clef-omni vs Clef vs Clef-flash vs Jev
Feature Clef-omni Clef Clef-flash Jev Developer Cloudflare Cloudflare Cloudflare TypeSafe AI Parameters 30B total, 3B active (MoE) 27B dense 9B dense Not disclosed Base model Qwen3-Omni-30B-A3B-Instruct Qwen3.8-27B Qwen3.5-9B Not disclosed Inputs Text, image, audio, video Text, image, video frames Text, image, video frames Text (per Cloudflare ) Hosted context 64,000 tokens 64k 24k (256k self-hosted) Not disclosed by TypeSafe (Cloudflare cites 32k) Input price per M tokens $0.15 $0.24 $0.038 $0.042 License Apache-2.0 Apache-2.0 Apache-2.0 API only, early access BANKING77 (macro-F1) 94.8 94.20 90.93 79.74 CLINC150+OOS (macro-F1) 97.7 97.43 66.77 89.27 When2Call (accuracy) 63.3 72.37 65.58 80.97 BRIGHT (nDCG@10) 42.0 45.91 39.26 47.52 Invoice processing, primary action 82.0 86.2 73.3 83.1
Benchmark scores are from Cloudflare’s announcement and were not independently verified.
