Qwen 2.5 VL 72B Instruct

ReasoningTool CallingAttachmentsOpen WeightsStructured Output

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

Providers8

ReleasedSep 1, 2024

Input Modalitiestext, image, audio, video

Output Modalitiestext

Tarsk Usecoding

Available Providers (8)

Provider	Model ID	Input Cost	Output Cost	Context	Max Output
NovitaAI	`qwen/qwen2.5-vl-72b-instruct`	$0.80/MTok	$0.80/MTok	32.8K	32.8K
Kilo Gateway	`qwen/qwen2.5-vl-72b-instruct`	$0.80/MTok	$1/MTok	128K	115.2K
OpenRouter	`qwen/qwen2.5-vl-72b-instruct`	$0.80/MTok	$1/MTok	128K	115.2K
OVHcloud AI Endpoints	`qwen2.5-vl-72b-instruct`	$1.01/MTok	$1.01/MTok	32.8K	32.8K
Cortecs	`qwen2.5-vl-72b-instruct`	$1.01/MTok	$1.01/MTok	32K	32K
Alibaba (China)	`qwen2-5-vl-72b-instruct`	$2.29/MTok	$6.88/MTok	131.1K	8.2K
Alibaba	`qwen2-5-vl-72b-instruct`	$2.80/MTok	$8.40/MTok	131.1K	8.2K
Qiniu	`qwen2.5-vl-72b-instruct`	—/MTok	—/MTok	128K	8.2K

Reasoning

Tool Calling

Attachments

Open Weights

Structured Output