Qwen2.5 72B Instruct
Qwen2.5 72B Instruct is a capable open-weight model with solid tool-use and function-calling support at a competitive price, though its intelligence index of 15.6 places it in the lower tier of current models and it has been superseded by newer Qwen releases.
Assessment date: April 4, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
Performance Profile
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
| Modality | Text → Text |
| Tokenizer | Qwen |
| Instruct Type | chatml |
| Parameters | 72B |
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 efficient models.
Model Information
| OpenRouter ID |
qwen/qwen-2.5-72b-instruct
|
| Provider | qwen |
| Release Date | September 19, 2024 |
| Context Length | 32,768 tokens |
| Max Completion | 16,384 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.12 | $0.000120 |
| Output | $0.39 | $0.000390 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
