Skip to main content
Alibaba DAMOReleased September 19, 2024

Qwen 2.5 72B

Open Source#6 Arena Rank72B parameters

Qwen 2.5 72B ranks in the top 10 on the Arena leaderboard. Context window: 0.128K tokens.

Context

128K

Input

Free (open)

Key Specifications

🏆

Arena Rank

#6

📐

Context Window

128K

📥

Input Price

per 1M tokens

Free (open)

📤

Output Price

per 1M tokens

Free (open)

🧠

Parameters

72B

🔓

Open Source

Yes

Best For

Multilingualcodingmathreasoning

About Qwen 2.5 72B

Qwen 2.5 72B, developed by Alibaba DAMO Academy, is a high-capability open-source model with 72 billion parameters and a 128K token context window. The model demonstrates strong performance across multilingual understanding, coding, mathematical reasoning, and general knowledge tasks, with particular strength in Chinese and English. Trained on a diverse corpus exceeding 18 trillion tokens, Qwen 2.5 72B achieves competitive scores against proprietary models on major benchmarks including MMLU, HumanEval, and GSM8K. Free and open-source under a permissive license, it supports commercial deployment and fine-tuning. The model has been widely adopted across the Asian developer community and serves as a foundation for numerous specialized applications. Qwen 2.5 72B ranks #6 on the Chatbot Arena leaderboard, confirming its position among the strongest open-weight models globally.

Pricing per 1M tokens

Input Tokens

Free (open)

Output Tokens

Free (open)

Other Alibaba DAMO Models

Frequently Asked Questions

What is Qwen 2.5 72B?
Qwen 2.5 72B, developed by Alibaba DAMO Academy, is a high-capability open-source model with 72 billion parameters and a 128K token context window. The model demonstrates strong performance across multilingual understanding, coding, mathematical reasoning, and general knowledge tasks, with particular strength in Chinese and English. Trained on a diverse corpus exceeding 18 trillion tokens, Qwen 2.5 72B achieves competitive scores against proprietary models on major benchmarks including MMLU, HumanEval, and GSM8K. Free and open-source under a permissive license, it supports commercial deployment and fine-tuning. The model has been widely adopted across the Asian developer community and serves as a foundation for numerous specialized applications. Qwen 2.5 72B ranks #6 on the Chatbot Arena leaderboard, confirming its position among the strongest open-weight models globally.
How much does Qwen 2.5 72B cost?
Qwen 2.5 72B costs Free (open) per 1M input tokens and Free (open) per 1M output tokens. You pay only for what you use, which keeps costs predictable.
What is Qwen 2.5 72B's context window?
Qwen 2.5 72B has a context window of 128K tokens. This determines how much text the model can process in a single request — bigger windows mean longer documents and richer conversation history.
Is Qwen 2.5 72B open source?
Yes, Qwen 2.5 72B is open source. The model weights are publicly available, so developers can download, fine-tune, and self-host it. Open-source models give teams more control over data privacy and deployment.
What is Qwen 2.5 72B best for?
Qwen 2.5 72B is best suited for: Multilingual, coding, math, reasoning. These use cases play to the model's strengths in capability, speed, and cost within Alibaba DAMO's lineup.