Qwen2.5 72B Instruct
Analysis Summary
Qwen2.5 72B Instruct is Alibaba's mid-2024 flagship open-weight model, offering tool use and function calling alongside a 131K context window. Its intelligence index of 9.6 places it in the lower tier of benchmarked models, but its MMLU-Pro score of 0.72 and GPQA of 0.491 indicate reasonable general knowledge and reasoning for its class.
For businesses, it suits cost-sensitive workloads such as structured content generation, SEO copy, and lightweight tool-calling pipelines. The very low pricing ($0.36 input, $0.40 output per 1M tokens) makes it attractive for high-volume automation. Agentic performance is limited, and coding capability is modest, so it is not suited to complex software engineering or multi-step agent tasks.
Teams looking for an affordable, capable model for content and structured output workflows will find it a practical option, particularly where budget constraints rule out frontier models.
Assessed June 30, 2026
Editorial notes
Qwen2.5 72B Instruct offers strong instruction following, tool use, and function calling at very competitive pricing, though its intelligence index places it well below current frontier models.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Qwen2.5 72B Instruct compares
Qwen2.5 72B Instruct ranks #236 of 385 AI models we track for overall intelligence, #185 of 293 for agentic tasks. Its 131K-token context window is larger than 59% of the models we list. At $0.36 per million input tokens it is cheaper than 39% of comparable models.
About Qwen2.5 72B Instruct
Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and..
Capabilities
Architecture Detail
| Instruct Type | chatml |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Qwen2.5 72B Instruct stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
qwen/qwen-2.5-72b-instruct
|
| Provider | qwen |
| Release Date | September 19, 2024 |
| Context Length | 131,072 tokens |
| Max Completion | 16,384 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.36 | $0.000360 |
| Output | $0.40 | $0.000400 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about Qwen2.5 72B Instruct
How much does Qwen2.5 72B Instruct cost?
Qwen2.5 72B Instruct costs $0.36 per million input tokens and $0.40 per million output tokens.
What is the context window of Qwen2.5 72B Instruct?
Qwen2.5 72B Instruct has a context window of 131,072 tokens (131K).
What can Qwen2.5 72B Instruct do?
Qwen2.5 72B Instruct supports tool use and function calling.
Who created Qwen2.5 72B Instruct?
Qwen2.5 72B Instruct is developed by Qwen and was released on September 19, 2024.
