Qwen3.5 Plus

alibaba

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of task evaluations, the 3.5 series consistently demonstrates performance on par with state-of-the-art leading models. Compared to the 3 series, these models show a leap forward in both pure-text and multimodal capabilities.

Try Now

Capabilities

Tool Use

Image Input

Extended Thinking

Example Use Cases

Balanced alibaba multimodal task

Text or vision reasoning at moderate cost

Long-context multimodal understanding with alibaba

Technical Specifications

Context Window

1,000,000 tokens

Max Output

65,536 tokens

Cache Miss Cost

$0.40 per 1M tokens

Non-Reasoning Cost

$2.40 per 1M tokens

Cache Read Cost

$0.04 per 1M tokens

Cache Write Cost

$0.50 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls