All Models

Qwen 3.5 4B

qwenReasoningTool CallingAttachmentsOpen WeightsStructured Output

Qwen vision-language model for visual reasoning, documents, and agent tasks

Providers3
ReleasedNov 1, 2025
Input Modalitiestext, image, video
Output Modalitiestext
Tarsk Usecoding

Benchmarks

13.1
Intelligence Index
22.6
Coding Index

Available Providers (3)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
SiliconFlow (China)Qwen/Qwen3.5-4B$0/MTok$0/MTok262.1K65.5K
QVACqwen3.5-4b$0/MTok$0/MTok32.8K8.2K
EmpirioLabs AIqwen3-5-4b$0.04/MTok$0.07/MTok262.1K32.8K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output