Qwen3-Omni
by Alibaba
· QWEN3 family · released Sep 24, 2025
Open weights
Active
Qwen3-Omni is a natively full-modal model (text/image/audio/video in, text and speech out) with an extended thinking mode, open-weights under Apache 2.0. Recognized as a top open omni-modal model on release in September 2025.
No pricing recorded for this model yet.
Specifications
| Model type | Multimodal |
|---|---|
| Architecture | MoE |
| Parameters | 235 (22 active) |
| Context window | Not disclosed tokens |
| Max output | Not disclosed tokens |
| Knowledge cutoff | Not disclosed |
| License | Apache License 2.0 |
| Modalities | Text input Image input Audio input Video input Text output Audio output |
| Tags | Vision |
| End of life | Not disclosed |
| Weights | Download |
| Official page | Link |
| Last verified | Not disclosed |