Qwen 2.5 72B

Alibaba CloudbalancedOpen Source

Alibaba's flagship open-source model. Competitive with GPT-4o class models on benchmarks at a fraction of the cost.

Context Window

131K

tokens

Max Output

8K

tokens

Input Price

$0.3

per 1M tokens

Output Price

$0.9

per 1M tokens

Speed

85

tokens/sec

Released

Sep 2024

2024-09-19

Blended Cost

$0.60

per 1M tokens

Value Score

133.3

quality per $

Capabilities

ChatCode GenerationFunction Calling

Benchmarks

Quality Index
80
MMLU Pro
85.3
HumanEval (Coding)
86.4
MATH
78.9
Arena ELO
1255

Open Source — Licensed under Apache 2.0

About Qwen 2.5 72B

Qwen 2.5 72B is a balanced AI model by Alibaba Cloud, released on September 19, 2024. It supports a context window of 131K tokens and can generate up to 8K output tokens.

At $0.3 per million input tokens and $0.9 per million output tokens, its blended cost of $0.60/1M tokens makes it one of the most affordable models available. Its value score of 133.3 reflects the balance of quality and cost.

Qwen 2.5 72B is available as an open-source model under the Apache 2.0 license, meaning you can self-host it for predictable costs or use it through API providers like Swfte Connect.

Using Qwen 2.5 72B with Swfte

Access Qwen 2.5 72B through Swfte Connect, our unified LLM gateway. Connect gives you a single API for 50+ models, with automatic routing, cost optimization, and fallback handling. You can also try Qwen 2.5 72B in our AI Playground before integrating.