Overview
The native omni-modal Flash service model in the Qwen3.8 line, with up to 1M context and text, image, audio, and video inputs.
Qwen3.8-Omni-Flash
The native omni-modal Flash service model in the Qwen3.8 line, with up to 1M context and text, image, audio, and video inputs.
QwenCloud listed `qwen3.8-omni-flash` on 2026-09-18; it is compatible with DashScope and OpenAI protocols and targets multimodal agents, video editing, music video, film production, summarization, and audio-video dialogue.
MODEL NUMBER098
- First public date
- 2026-09-18
- Organization
- Alibaba Cloud
- Family
- Qwen
01
Specifications
Only published specifications are shown.
- Context
- 1,000,000 tokens
- Input modalities
- Text · Image · Audio · Video
- Open weights
- No
- Status
- Current
02
Overview
Why it mattered
It extends Qwen3.8-Flash-Next agentic capability into unified audio-video understanding and multimodal workflows with DashScope and OpenAI protocol access.
03
Architecture & capabilities
Model capabilities
Native multimodalNative audioCodingAgentTool useLong context
04
Release history
QwenCloud released qwen3.8-omni-flash: a native omni-modal model with up to 1M context, text/image/audio/video inputs, and DashScope/OpenAI protocol compatibility.
View source05
Related models
Select a card to view the related model.
06
Sources
Suggest a correction
Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.