---
name: Qwen 3.7 Flash
slug: 3-7-flash
type: Multimodal
providers:
  - vercel
description: 'Qwen vision-language model for visual reasoning, documents, and agent tasks'
tags:
  - multimodal
is_open_source: false
context_window: 991000
max_output: 64000
pricing:
  - image: 0
    input: 0.03
    output: 0.13
    provider: vercel
release_date: '2026-07-28'
capabilities:
  audio: false
  vision: true
  tool_use: false
  citations: false
  reasoning: false
---
Qwen 3.7 Flash is a Multimodal model.
Qwen vision-language model for visual reasoning, documents, and agent tasks