Qwen: Qwen3.5 397B A17B

QwenID: 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 attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers state-of-the-art performance comparable to leading-edge models across a wide range of tasks, including language understanding, logical reasoning, code generation, agent-based tasks, image understanding, video understanding, and graphical user interface (GUI) interactions. With its robust code-generation and agent capabilities, the model exhibits strong generalization across diverse agent.

Pricing per 1M Tokens

Input (Prompt)$0.39
Output (Completion)$2.34
Cache ReadFree
Cache WriteFree
ImageN/A

Specifications

Context Length262K
Max Output Tokens66K
Input ModalitiesText + Image + Video
Output ModalitiesText
TokenizerQwen3
Instruct TypeN/A
Top Provider Context262K
Top Provider Max Output66K
ModeratedNo

Compare this model

See how Qwen: Qwen3.5 397B A17B stacks up against other models.

More from Qwen

Last updated: March 23, 2026

First tracked: March 23, 2026