---
name: Qwen 2.5 Vl 72B Instruct
slug: 2-5-vl-72b
type: Multimodal
providers:
  - qiniu-ai
description: 'Qwen vision-language model for visual reasoning, documents, and agent tasks'
tags:
  - tool-use
  - multimodal
is_open_source: false
context_window: 128000
max_output: 8192
release_date: '2025-08-05'
capabilities:
  audio: true
  vision: true
  tool_use: true
  citations: false
  reasoning: false
---
Qwen 2.5 Vl 72B Instruct is a Multimodal model.
Qwen vision-language model for visual reasoning, documents, and agent tasks