Qwen3 VL 235B A22B Thinking

alibaba

Qwen3 series VL models feature significantly enhanced multimodal reasoning capabilities, with a particular focus on optimizing the model for STEM and mathematical reasoning. Visual perception and recognition abilities have been comprehensively improved, and OCR capabilities have undergone a major upgrade.

Try Now

Capabilities

Tool Use

Image Input

Extended Thinking

Example Use Cases

Hardest visual reasoning task

Stem or math with image input

Complex multimodal analysis requiring thinking

Technical Specifications

Context Window

131,072 tokens

Max Output

32,768 tokens

Cache Miss Cost

$0.40 per 1M tokens

Non-Reasoning Cost

$4 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

⚠️ Legacy

Made legacy on

Reason

Outdated model

Recommended Replacement

Qwen3.5 Plus