OpenRouter 上线 Clef Omni 音视频输入，支持四种模态单次调用
We fed Clef Omni a photo, 3 seconds of sizzle, a 2-second clip of a hot dog stand, and the word "lunch?"
OpenRouter 宣布 Decisions 的音视频输入正式上线，Clef Omni 可在一次调用中同时处理图像、音频、视频和文本，并直接返回概率而非 token。官方演示中，输入一张照片、3 秒滋滋声、2 秒热狗摊视频和“lunch?”一词，模型给出 hot dog 96.5%。该请求共 801 个输入 token，费用 $0.00012，定价为 $0.15/M 输入、输出免费。
推荐理由
AI 评分 60
OpenRouter 上线 Clef Omni 的音视频输入，并给出单次调用成本，读者可据此判断多模态决策接口的可用性。
主题
查看原帖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. https://t.co/UKDp0OKHHA
正文
当前显示原文，中文全文译文尚未就绪。
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. https://t.co/vHqUjoUqNG