Qwen3-VL 235B (Instruct)
by Alibaba
· QWEN3 Vl family · released Oct 14, 2025
Open weights
Active
Open-weight flagship vision-language MoE (235B total / 22B active) with 256K context, strong OCR/document parsing, video understanding, and GUI agent capability; the leading open multimodal model at release.
No pricing recorded for this model yet.
Specifications
| Model type | Multimodal |
|---|---|
| Architecture | MoE |
| Parameters | 235 (22 active) |
| Context window | 262.1K tokens |
| Max output | Not disclosed tokens |
| Knowledge cutoff | Not disclosed |
| License | Apache License 2.0 |
| Modalities | Text input Image input Video input Text output |
| Tags | Agentic Long context Vision |
| End of life | Not disclosed |
| Weights | Download |
| Last verified | Not disclosed |