Back to Models

Qwen: Qwen3.5 Plus 2026-02-15

qwen3.5-plus-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...

Modalities

Input

textimagevideo

Output

text
Pricing
Cost per 1 million tokens
Input
$0.312
Output
$1.872
Model Specs
Context Window
1,000,000
Max Output
65,536
Release Date
2026-02-16
Knowledge Cutoff
2025-04
Capabilities
Reasoning
Tool Calling
Vision

Last Updated: 2026-02-16

Provider: