Alibaba Qwen Releases Qwen3.8-Omni-Flash: A 1M-Context Omni-Modal Model Built Around Agentic Audio-Video Understanding and Tool Use
Alibaba's Qwen team launched Qwen3.8-Omni-Flash, an API-only omni-modal model with 1M-token context and agentic audio-video understanding and tool use.
Qwen3.8-Omni-Flash accepts text, images, audio, and video and returns text, built on the Qwen3.8-Flash-Next architecture with a 1M-token context window and thinking enabled by default. Qwen reports a 25%+ average improvement over Qwen3.5-Omni-Plus across 29 evaluations, with OmniVideoBench rising from 63.4 to 67.8 while using about 45.7% fewer tokens via coarse-to-fine agentic perception. It is hosted on QwenCloud, Model Studio, and Qwen Studio at $0.15/$0.47 per 1M input/output tokens; no open weights were released, but Qwen open-sourced Qwen-MM-Plugins under Apache-2.0.
- Agentic perception gathers evidence coarse-to-fine instead of processing long video linearly
- Qwen claims audio-visual performance near Gemini 3.8 Flash and audio above it
- Audio input in 113 languages; video up to 2 hours/2 GB; available in 6 regions
- Qwen-MM-Plugins adds omni-memory, omni-video2note, and omni-chatcut skills for agent harnesses
From the original article
4 min read at marktechpost.com
Alibaba's Qwen3. 8-Omni-Flash understands audio and video, plans tasks, calls tools, and reports about 45. 7% fewer tokens on OmniVideoBench.
By Asif Razzaq · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.