AgentHub

Qwen: Qwen3.5 397B A17B

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear at…

Live
Open / InstallLast updated July 27, 2026

Description

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...

Author

qwen

Platform

api

Pricing model

paid

Categories

Design

Tags

openrouter
llm
qwen
text
image
video

Capabilities

  • Image input
  • 262,144 token context