Skip to main content
Back to models

Model comparison

Compare model identity and capabilities.

Selected

Qwen2.5-VL 72B Instruct

alibaba/qwen2-5-vl-72b-instruct

Alibaba / Qwen

View model

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

Released
2024-09
Context window
131K
Max output
8.2K
Weights
Open weight
Modalities
TextInputImageInputTextOutput
Capabilities
Tool callTemperatureOpen weightStructured
Providers
AlibabaAlibaba (China)Kilo GatewayLLM GatewayNovitaAIOpenRouterOVHcloud AI EndpointsQiniu

Select at least two models to compare.

Compare models
1 models selected
Compare