All Models

QVQ Max

qwenReasoningTool CallingAttachmentsOpen Weights

Compact GPT model for low-latency assistance and high-volume workloads

Providers3
ReleasedMar 25, 2025
Input Modalitiestext, image
Output Modalitiestext
Tarsk Usecoding

Available Providers (3)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
Alibaba (China)qvq-max$1.15/MTok$4.59/MTok131.1K8.2K
NanoGPTqvq-max$1.20/MTok$4.80/MTok128K8.2K
Alibabaqvq-max$1.20/MTok$4.80/MTok131.1K8.2K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output