All Models

Qwen3 VL 32B Instruct

qwenTool CallingAttachmentsOpen WeightsStructured Output

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

Providers4
ReleasedOct 21, 2025
Input Modalitiestext, image
Output Modalitiestext
Tarsk Usecoding

Benchmarks

8.4
Intelligence Index
68.3
Math Index

Available Providers (4)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
Kilo Gatewayqwen/qwen3-vl-32b-instruct$0.10/MTok$0.42/MTok131.1K32.8K
OpenRouterqwen/qwen3-vl-32b-instruct$0.10/MTok$0.42/MTok131.1K32.8K
SiliconFlow (China)Qwen/Qwen3-VL-32B-Instruct$0.20/MTok$0.60/MTok262K262K
SiliconFlowQwen/Qwen3-VL-32B-Instruct$0.20/MTok$0.60/MTok262K262K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output