All Models

Qwen 2.5 VL 32B Instruct

qwenTool CallingAttachmentsOpen WeightsStructured Output

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

Providers2
ReleasedNov 1, 2024
Input Modalitiestext, image
Output Modalitiestext
Tarsk Usecoding

Available Providers (2)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
IO.NETQwen/Qwen2.5-VL-32B-Instruct$0.05/MTok$0.22/MTok32K4.1K
MeganovaQwen/Qwen2.5-VL-32B-Instruct$0.20/MTok$0.60/MTok16.4K16.4K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output