Qwen

Qwen2.5 72B Instruct

CTX131K

40Quality

Tools

Input$1.40/M

Output$5.60/M

Qwen instruction model for multilingual chat, reasoning, and tool use

Open weightsQwen license383/1044

Drag to turn

QwenTextUncommon

Qwen2.5 72B Instruct

Qwen instruction model for multilingual chat, reasoning, and tool use

qwen2-5-72b-instruct

Type: Text
Quality: 40 · Top 60% on the Epoch Capabilities Index
Context window: 131,072 tokens
Max output: 8,192 tokens
Input price: $1.40 / 1M tokens
Output price: $5.60 / 1M tokens
Cache read: —
Cache write: —
Parameters: 73B (72,706,203,648)
Downloads: 250K in the last 30 days
Likes: 1K
Access to weights: Open download
Released: Sep 1, 2024
Knowledge cutoff: Apr 2024
Takes in: Text
Puts out: Text
Reasoning: No
Tool calling: Yes
Structured output: No
File attachments: No
Access: Open weights
License: Qwen license
Rarity: Uncommon
Set number: 383/1044

Open Qwen docs Weights on Hugging Face Quality 40 Where to run it 10 Evolution 4/8 Race it 34 tok/s Meet its creature Battle Grok 4.7

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 72B Instruct, refreshed daily from Epoch AI and LMArena.

Top 60% of the 277 models on the Epoch Capabilities Index: #167.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

Epoch Capabilities Index#167 of 277
One number fitted from dozens of hard benchmarks, from science questions to agentic coding.129.0 index
Listed as Qwen2.5-72B
LMArena Text#282 of 416
People compare two anonymous answers and vote for the better one.1,269 rating
LMArena Text · Coding#262 of 411
The text arena’s coding prompts only.1,292 rating
LMArena Text · Math#249 of 400
The text arena’s math prompts only.1,283 rating
LMArena Text · Creative writing#294 of 414
The text arena’s creative writing prompts only.1,221 rating

Benchmarks Epoch AI runs

Scores from Epoch AI and LMArena, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

8 providers sell Qwen2.5 72B Instruct through an API, and 2 Hugging Face hosts serve it. Prices are per million tokens, cheapest first.

CheapestAbacus$0.11 in · $0.38 out
From the labAlibaba$1.40 in · $5.60 out
Fastest on Hugging FaceDeepInfra34 tokens/s

API providers

Provider	Input	Output	Context
AbacusCheapest paid`Qwen/Qwen2.5-72B-Instruct`	$0.11	$0.38	128K
Kilo Gateway`qwen/qwen-2.5-72b-instruct`	$0.36	$0.40	33K
NanoGPT`qwen/qwen-2.5-72b-instruct`	$0.36	$0.40	131K
OpenRouter`qwen/qwen-2.5-72b-instruct`	$0.36	$0.40	33K
SiliconFlow`Qwen/Qwen2.5-72B-Instruct`	$0.59	$0.59	33K
SiliconFlow (China)`Qwen/Qwen2.5-72B-Instruct`	$0.59	$0.59	33K
Alibaba (China)`qwen2-5-72b-instruct`	$0.57	$1.72	131K
AlibabaOfficial`qwen2-5-72b-instruct`	$1.40	$5.60	131K

Hugging Face Inference Providers

Host	Input	Output	Context	Speed	First token
DeepInfraFastestTools	$0.36	$0.40	33K	34 tok/s	0.2s
Featherless	—	—	—	—	—

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.