Qwen2.5-VL 72B Instruct

unknown

Alibaba · qwen family

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

Limits

Context131,072
InputUnknown
Output8,192

Modalities

Inputtext, image
Outputtext

Release info

Release2024-09
Last update2024-09
Knowledge cutoff2024-04

Provider offerings

Provider-specific prices and limits stay separate from canonical model facts.

ProviderProvider model IDInputOutputContextOutput limit
Alibaba (China)qwen2-5-vl-72b-instruct$2.294 / 1M$6.881 / 1M131,0728,192
LLM Gatewayqwen2-5-vl-72b-instruct$0.13 / 1M$0.4 / 1M32,7688,192
Alibabaqwen2-5-vl-72b-instruct$2.8 / 1M$8.4 / 1M131,0728,192
Qiniuqwen2.5-vl-72b-instructUnknownUnknown128,0008,192
OVHcloud AI Endpointsqwen2.5-vl-72b-instruct$1.01 / 1M$1.01 / 1M32,76832,768
Kilo Gatewayqwen/qwen2.5-vl-72b-instruct$0.8 / 1M$0.8 / 1M32,76832,768
OpenRouterqwen/qwen2.5-vl-72b-instruct$0.8 / 1M$1 / 1M131,072128,000
NovitaAIqwen/qwen2.5-vl-72b-instruct$0.8 / 1M$0.8 / 1M32,76832,768
Nebius Token FactoryQwen/Qwen2.5-VL-72B-Instruct$0.25 / 1M$0.75 / 1M128,0008,192
NanoGPTTEE/qwen2.5-vl-72b-instruct$0.7 / 1M$0.7 / 1M65,5368,192

Capabilities

Attachments

No

Reasoning

No

Tool calling

Yes

Structured output

Unknown

Temperature

Yes