Back to Models

Qwen: Qwen3.5-35B-A3B

qwen3.5-35b-a3b

The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...

Modalities

Input

textimagevideo

Output

text
Pricing
Cost per 1 million tokens
Input
$0.167
Output
$1.2
Model Specs
Context Window
262,144
Max Output
81,920
Release Date
2026-02-25
Knowledge Cutoff
Capabilities
Reasoning
Tool Calling
Vision

Last Updated: 2026-02-25

Provider: