MaxCompute - MaxFrame AI Function now supports multimodal mixed input.
Jul 30 2026
MaxComputeMaxFrame AI Function now supports multimodal mixed input, allowing any combination of text, images, audio, and video in a single call. Integrated with the Bailian Qwen-Omni all-modal model, it enables cross-modal joint inference and batch processing of multimodal data.
Content
Target customers: All customers. New features /specifications: MaxFrame AI Function now supports multimodal mixed input, allowing any combination of text, images, audio, and video in a single call. Integrated with the Bailian Qwen-Omni all-modal model, it enables cross-modal joint inference and batch processing of multimodal data.