Qwen2.5-72B

Name: Qwen2.5-72B
Price: 0.004 CNY
Availability: InStock
Author: Alibaba

Foundation modelQwen2.5

Qwen2.5-72B

Release date: 2024-09-18Updated: 2024-09-21Views: 1,754

Live demoGitHub Hugging Face Compare

Parameters

72.7B

Context length

128K

Multilingual

Supported

Reasoning ability

No data

Qwen2.5-72B is an AI model published by Alibaba, released on 2024-09-18, for Foundation model, with 72.7B parameters, and 128K context length, requiring about 144GB storage, with a 91.50 score on GSM8K.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Qwen2.5-72B

Model basics

Reasoning traces

No data

Thinking modes

Thinking modes not supported

Context length

128K tokens

Max output length

No data

Model type

Foundation model

Modality (in / out)

No data

Release date

2024-09-18

Model file size

144GB

MoE architecture

Total params / Active params

72.7B / Not applicable

Knowledge cutoff

No data

Qwen2.5-72B

Open source & experience

Code license

Apache 2.0

Weights license

Qwen License- Commercial use permitted

GitHub repo

github.com/QwenLM/Qwen2.5

Hugging Face

huggingface.co/Qwen/Qwen2.5-72B

Live demo

N/A

Qwen2.5-72B

Official resources

Paper

DataLearnerAI blog

N/A

Qwen2.5-72B

API details

API speed

No data

💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.

Learn about pricing modes

Standard

Type	Condition	Input	Output
Text	-	¥0.0040/ 1K tokens	¥0.012/ 1K tokens

“—” means the modality is not billed in that direction, or the vendor has not published a price for it.

Qwen2.5-72B

Benchmark Results

Qwen2.5-72B currently shows benchmark results led by MBPP (13 / 96, score 84.70), GSM8K (13 / 70, score 91.50), TruthfulQA (1 / 4, score 60.40). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.