Home/Models/Qwen 2.5 72B

Qwen 2.5 72B

Open Source
by Alibaba· Released 2024-09
Official Docs ↗

Qwen 2.5 72B is Alibaba's most capable open-weight model, offering exceptional value especially for multilingual applications. It outperforms Llama 3.1 70B on several benchmarks at a similar price point.

Input Price
$0.35/1M
per 1M tokens
Output Price
$0.40/1M
per 1M tokens
Context Window
131K tokens
max tokens
ELO Score
1280
LMSYS Arena

Pricing Breakdown

VolumeInput CostOutput CostCombined (50/50)
1,000 tokens$0.0003$0.0004$0.0004
10,000 tokens$0.0035$0.0040$0.0038
100,000 tokens$0.0350$0.0400$0.0375
1,000,000 tokens$0.3500$0.4000$0.3750

Strengths

  • Best-in-class for Chinese/Japanese/Korean languages
  • Open source weights available
  • Strong coding performance for cost
  • Competitive with Llama 405B at 72B size

Weaknesses

  • Less optimized for pure English tasks
  • Fewer hosted providers than Llama

Best For

translationcodinglow costdata extraction

Compare Qwen 2.5 72B With

Qwen 2.5 72B vs o3
OpenAI
Qwen 2.5 72B vs DeepSeek R1
DeepSeek
Qwen 2.5 72B vs o1
OpenAI
Qwen 2.5 72B vs Gemini 2.0 Flash
Google
Qwen 2.5 72B vs DeepSeek V3
DeepSeek
Qwen 2.5 72B vs Claude Sonnet 4.6
Anthropic

Frequently Asked Questions

How much does Qwen 2.5 72B cost?

Qwen 2.5 72B costs $0.35/1M per 1M input tokens and $0.40/1M per 1M output tokens.

What is Qwen 2.5 72B's context window?

Qwen 2.5 72B has a context window of 131K tokens, which means it can process up to 131,072 tokens in a single request.

Is Qwen 2.5 72B open source?

Yes, Qwen 2.5 72B is open source. The model weights are publicly available and can be self-hosted.

What is Qwen 2.5 72B best used for?

Qwen 2.5 72B is best suited for: translation, coding, low-cost, data-extraction. Best-in-class for Chinese/Japanese/Korean languages.

What is Qwen 2.5 72B's ELO score?

Qwen 2.5 72B has an ELO score of 1280 on the LMSYS Chatbot Arena leaderboard, placing it in the mid-tier range.