Qwen: Qwen3.5-35B-A3B

Developed by qwen

API Pricing (per 1M tokens)

Input$0.25

Output$2.00

Intelligence Benchmarks

MMLU ProN/A

GPQAN/A

Intelligence IndexN/A

LivebenchN/A

Technical Specifications

Context Window	262K Tokens
Vision Support	Yes
Tokens per Second	N/A
Time to First Token (s)	N/A
Modalities	textimagevideo->text

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