Qwen3.8 Omni Flash
Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...
The figures
- Made by
- Qwen
- Model ID
- qwen/qwen3.8-omni-flash
- Input
- $0.15 per million tokens
- Output
- $0.47 per million tokens
- Context window
- 1M tokens
- Longest answer
- 131K tokens
- Takes in
- text, image, audio, video
- Gives back
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Reads images
- Yes
- Open weights
- No
- Released
- 21 Sept 2026
Read on 3 Oct 2026.