Qwen Models
Qwen logo

Qwen3.5-35B-A3B

35B

by Qwen

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 performance is comparable to that of the Qwen3.5-27B.

Chat with Qwen3.5-35B-A3B
Input Price$0.25/1M tokens
Output Price$2.00/1M tokens
Intelligence37.0
Coding30.3

Specifications

Technical details and pricing.

ProviderQwen
Context Window262,144 tokens
Release DateFeb 24, 2026
ModalitiesText, Image, Video β†’ Text
CapabilitiesVision

Benchmarks

7 benchmark scores from Artificial Analysis.

GPQA84.5%
HLE19.7%
SciCode37.7%
LCR62.7%
IFBench72.5%
Tau289.2%
TerminalBench Hard26.5%

Composite Indices

Intelligence, Coding, Math

Standard Benchmarks

Academic and industry benchmarks

Frequently Asked Questions

What is Qwen3.5-35B-A3B good for?

Use Qwen3.5-35B-A3B for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Qwen3.5-35B-A3B cost?

Pricing is based on usage. Current rates are $0.25/1M tokens for input and $2.00/1M tokens for output.

Can I try Qwen3.5-35B-A3B for free?

Yes. You can start a chat instantly and test the model before deciding on a plan.

Does Qwen3.5-35B-A3B support images or audio?

Qwen3.5-35B-A3B can understand images.

Benchmarks and pricing are sourced from Artificial Analysis where available. OpenRouter specs are used as a fallback.