Qwen3.5 Plus 2026-02-15
The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of task evaluations, the 3.5 series consistently demonstrates performance on par with state-of-the-art leading models.
Input
Output
Context
1000K
Max Output
66K
Parameters
—
Technical Specifications
Model TypeVision
Context Window1.0M
Max Output Tokens66K
Parameters—
Training Cutoff—
Licenseapache-2.0
Capabilities
Input Modalities
textimagevideo
Output Modalities
text
Features
function_callingjson_modereasoningstreamingtext_generationvision
Resources & Links
Related Tools
Data sourced from official provider APIs and documentation
Last updated: May 5, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.