Qwen

Qwen2.5-VL 7B Instruct

CTX131K

Vision · Tools

Input$0.35/M

Output$1.05/M

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

Open weightsApache 2.0386/1044

Drag to turn

QwenTextCommon

Qwen2.5-VL 7B Instruct

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

qwen2-5-vl-7b-instruct

Type: Text
Quality: Not rated yet
Context window: 131,072 tokens
Max output: 8,192 tokens
Input price: $0.35 / 1M tokens
Output price: $1.05 / 1M tokens
Cache read: —
Cache write: —
Parameters: 8.3B (8,292,166,656)
Downloads: 5.2M in the last 30 days
Likes: 1.7K
Access to weights: Open download
Released: Sep 1, 2024
Knowledge cutoff: Apr 2024
Takes in: Text, Image
Puts out: Text
Reasoning: No
Tool calling: Yes
Structured output: No
File attachments: No
Access: Open weights
License: Apache 2.0
Rarity: Common
Set number: 386/1044

Open Qwen docs Weights on Hugging Face Where to run it 3 Evolution 2/3 Meet its creature Battle GLM-4.5-Air

License read from the model’s Hugging Face card. Specs from models.dev, downloads from Hugging Face, last changed Oct 19, 2026. Official source: www.alibabacloud.com.

How good is it?

Public leaderboard scores for Qwen2.5-VL 7B Instruct, refreshed daily from Epoch AI and LMArena.

No public leaderboard lists Qwen2.5-VL 7B Instruct yet. Epoch AI and LMArena cover most chat, image, and video models from the big labs; embeddings, speech, and small open models mostly go unrated.

Where to run it

3 providers sell Qwen2.5-VL 7B Instruct through an API. Prices are per million tokens, cheapest first.

CheapestAlibaba (China)$0.29 in · $0.72 out
From the labAlibaba$0.35 in · $1.05 out

API providers

Provider	Input	Output	Context
Alibaba (China)Cheapest paid`qwen2-5-vl-7b-instruct`	$0.29	$0.72	131K
AlibabaOfficial`qwen2-5-vl-7b-instruct`	$0.35	$1.05	131K
Qiniu`qwen2.5-vl-7b-instruct`	—	—	128K

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current text models from other labs at a similar output price.