Alibaba’s Qwen team has released Qwen3.8-Omni-Flash, a native omni-modal model that can process text, images, audio and video in a single workflow. The model supports a 1-million-token context window and is now available through the Qwen AI platform.
Alibaba said Qwen3.8-Omni-Flash improved its average score by more than 26% across 30 evaluations compared with Qwen3.5-Omni-Plus. It also reported gains in audio-video agents, coding, long-context tasks and real-time multimodal interaction.
The model supports long-video analysis, meeting summaries, video research and multimodal tool use. Alibaba has also released Qwen-MM-Plugins and Qwen-Live Harness for long-running and real-time workflows. API input pricing has been reduced to as low as RMB 0.8 per million tokens. [IT Home, in Chinese]