Qwen3.5 35B A3B

alibaba

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.

Try Now

Capabilities

Image Input

Extended Thinking

Tool Use

Example Use Cases

Budget multimodal reasoning with alibaba

Lightweight moe with vision at minimal cost

Cost-sensitive text and image tasks

Technical Specifications

Context Window

256,000 tokens

Max Output

64,000 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input
≤ 128,000 input$0.057
> 128,000 input$0.229
Non-Reasoning Output
≤ 128,000 input$0.459
> 128,000 input$1.835

Tool Costs (per 1K calls)

Web Search

$15

Code Execution

$0.19

⚠️ Legacy

Made legacy on

Reason

Untested

Recommended Replacement

Qwen3.5 Plus