Qwen3.6 35B A3B

Name: Qwen3.6 35B A3B
Brand: Qwen
Price: 0.248 USD

35B

byQwen

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...

Chat withQwen3.6 35B A3B

Input Price$0.25/1M tokens

Output Price$1.49/1M tokens

Intelligence43.5

Coding35.1

Specifications

Technical details and pricing.

ProviderQwen

Context Window262,144 tokens

Release DateApr 16, 2026

ModalitiesText, Image, Video → Text

CapabilitiesVision

Benchmarks

7 benchmark scores from Artificial Analysis.

GPQA84.1%

HLE20.2%

SciCode35.8%

LCR63.7%

IFBench64.4%

Tau295.3%

TerminalBench Hard34.8%

Composite Indices

Intelligence, Coding, Math

Standard Benchmarks

Academic and industry benchmarks

Frequently Asked Questions

What is Qwen3.6 35B A3B good for?

Use Qwen3.6 35B A3B for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Qwen3.6 35B A3B cost?

Pricing is based on usage. Current rates are $0.25/1M tokens for input and $1.49/1M tokens for output.

Can I try Qwen3.6 35B A3B for free?

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

Does Qwen3.6 35B A3B support images or audio?

Qwen3.6 35B A3B can understand images.

Similar Models

Other models you might want to explore.

Qwen3.5-35B-A3B

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.

Details →

Qwen3.6 Plus

Qwen

Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference.

Details →

Qwen3.6 Flash

Qwen

Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series.

Details →

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