Hunyuan

混元（Hunyuan）的大规模视觉语言模型，支持文本与图像输入。在视觉理解、图像描述及多模态推理方面表现突出，适用于内容审核、辅助工具及视觉问答等场景。

Hunyuan's open-weight flagship built for real-world agentic work, using a sparse mixture-of-experts design of 770B total parameters with 49B active per token. Handles up to 1,048,576 input tokens and returns up to 64K tokens, accepting text, images, and video natively. Released under Apache 2.0 with BF16 and FP8 checkpoints, it targets long-horizon software engineering, cross-document analysis, game development, and scientific research.