🚀 Meet Qwen3.8-Omni-Flash, Qwen's first omni-modal model built around agentic capabilities!
Native audio-video understanding, reasoning, and tool use come together in one model: understand the content, plan the task, execute with tools, and deliver the result.
Highlights: 🥳
- Audio-video intelligence that gets things done: jointly reason over what's seen and heard, and orchestrate tools across long workflows to auto-edit vlogs, translate short videos, and turn movies into recaps.
- A major leap: approaching Gemini 3.8 Flash in audio-video capabilities; +19.5 points on average in agent performance across WildClawBench-MM & UniClawBench.
- 1M-token context with agentic perception: actively explore long videos and locate key moments with higher accuracy, using 51.8% fewer tokens than static understanding on OmniVideoBench.
Video input costs are reduced by about 89% compared with Qwen3.5-Omni-Plus, making long-form audio-video understanding and agentic workflows more affordable than ever.
To help you build apps around Omni, we're also open-sourcing Qwen-MM-Plugins and Qwen-Live Harness! 🛠️
We can't wait to see what you build with Qwen3.8-Omni-Flash! 👀
- Blog:…
Qwen's team says Qwen3.8-Omni-Flash is its first omni-modal model built specifically around agentic capability, combining native audio-video understanding with reasoning and tool useA model's ability to call external functions — run code, search the web, edit files — instead of only generating text.Full definition → in one model.
Alibaba's Qwen team reports the model approaches Gemini 3.8 Flash on audio-video capability and gains +19.5 points on average in AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → performance across the WildClawBench-MM and UniClawBench benchmarks, per its own announcement.
With a 1M-token context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition →, Qwen3.8-Omni-Flash actively explores long videos to locate key moments, using 51.8% fewer tokens than static understanding requires on the OmniVideoBench benchmark, according to Qwen.
Qwen says video input costs for the new model are about 89% lower than its predecessor Qwen3.5-Omni-Plus, a cut aimed at making long-form audio-video agentic workflows more affordable.
Alongside the model, Qwen is open-sourcing Qwen-MM-Plugins now, with a Qwen-Live agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition → for real-time use described as coming soon.
Terms in this piece · Glossary
tool use — A model's ability to call external functions — run code, search the web, edit files — instead of only generating text.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
Why it matters
Qwen3.8-Omni-Flash lets agents jointly parse audio and video and drive tool calls across long workflows, with a steep cost cut making long-form video agents commercially viable.
Read the full post on X ↗
