Cloudflare 推出 Clef-omni：单次调用处理音频、视频、图片、文本
We fed Clef Omni a photo, 3 seconds of sizzle, a 2-second clip of a hot dog stand, and the word "lun...
Cloudflare 新出的 Clef-omni 一次调用吃四种模态，直接输出概率，输出还免费。
Cloudflare 扩展 Clef 决策模型家族，新增 Clef-omni，可在单条流水线中原生处理音频、视频、图片和文本。官方演示中，一张照片、3 秒音频、2 秒视频加一个词“lunch?”输入后，模型给出 hot dog 分类及 96.5% 概率，结果以概率而非 token 形式返回。Clef-omni 已上线 OpenRouter，Decisions 的音频与视频输入同步开放，定价为每百万输入 token 0.15 美元，输出免费。同期 Clef-flash 价格下调，Clef 推理速度最高提升 2.0 倍。
We fed Clef Omni a photo, 3 seconds of sizzle, a 2-second clip of a hot dog stand, and the word "lun...
We fed Clef Omni a photo, 3 seconds of sizzle, a 2-second clip of a hot dog stand, and the word "lunch?" It said: hot dog, 96.5%. Audio + video input for Decisions is live on OpenRouter. Four modalities, one call, probabilities instead of tokens. $0.15/M input, output free. Your browser does not support the video tag. 🔗 View on Twitter Cloudflare @Cloudflare We are expanding the Clef decision model family with Clef-omni, natively processing audio, video, images, and text in a single pipeline. We’ve also lowered Clef-flash pricing and boosted Clef inference speeds by up to 2.0x. cfl.re/4s6nYeD 🔗 View Quoted Tweet 💬 1 🔄 1 ❤️ 5 👀 847 📊 1 ⚡
