Back to all models
qwen
qwenQwen: 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,...
qwen/qwen3.8-omni-flash
Context Size
1,000K
Input Price
22,500 pts/M1,384 Ks/M
Output Price
70,500 pts/M4,336 Ks/M
Architecture
Text
Image
Audio
Video
Supported Parameters
frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Details
TokenizerQwen
Max Completion131,072 tokens
Provider Context1,000K tokens
ModeratedNo
CreatedSep 21, 2026