modelbenchmark.io

Qwen3 Omni 30B A3B Thinking

Alibaba · qwen3-omni-30b-a3b-thinking

Compare

Multimodal reasoning model accepting text, images, video, and audio with text output

Specification

most-agreed values

Context
66K
Max output
16K
Released
2025-09-22
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text, image, video, audio
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.25
Output
$0.97

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
novita$0.25$0.97——66K16K—
novita-ai$0.25$0.97——66K16K—

More from Alibaba

most-hosted first