Qwen3.8-Omni-Flash, a next-generation native full-modal model, was officially launched. The core goal of the model is to enhance its agent capabilities in real productivity scenarios and push the full modal model further from “understanding full modal content” to “planning tasks, calling tools, and completing creations.” On the basis of having general agentic capabilities such as programming, text knowledge work, and GUI operation, Qwen3.8-Omni-Flash has further expanded Agentic applications with audio and video as the core, and has achieved remarkable results in video editing, music and video creation, film and television production and explanation, audio and video summaries, audio and video conversations, etc., which require comprehensive processing of text, images, audio, and video.

Qwen3.8-Omni-Flash, a next-generation native full-modal model, was officially launched. The core goal of the model is to enhance its agent capabilities in real productivity scenarios and push the full modal model further from “understanding full modal content” to “planning tasks, calling tools, and completing creations.” On the basis of having general agentic capabilities such as programming, text knowledge work, and GUI operation, Qwen3.8-Omni-Flash has further expanded Agentic applications with audio and video as the core, and has achieved remarkable results in video editing, music and video creation, film and television production and explanation, audio and video summaries, audio and video conversations, etc., which require comprehensive processing of text, images, audio, and video.