# 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 mathematics, thanks to our specialized expert models in these domains.

- Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots.

- Long-context Support up to 128K tokens and can generate up to 8K tokens.

- Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.

Usage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).

## Model Information

- **Organization**: [qwen](/llm.txt)
- **Slug**: qwen-2-5-72b-instruct
- **Available at Providers**: 27
- **Release Date**: September 19, 2024

### Benchmark Scores
- GPQA: 0.49

## Providers

| Provider | Name | $ Input (per 1M) | $ Output (per 1M) | Free | Link |
|----------|------|-----------------|------------------|------|------|
| [AIHubMix](/llm/aihubmix.txt) | qwen2.5-72b-instruct | 0.80 | 2.40 |  | [View](https://aihubmix.com/model/qwen2.5-72b-instruct) |
| [AIHubMix](/llm/aihubmix.txt) | Qwen2.5-72B-Instruct | 0.80 | 0.80 |  | [View](https://aihubmix.com/model/Qwen/Qwen2.5-72B-Instruct) |
| [Chutes.ai](/llm/chutes.txt) | Qwen2.5-72B-Instruct | 0.30 | 1.20 |  |  |
| [FastRouter](/llm/fastrouter.txt) | Qwen: Qwen2.5 72B Instruct | 0.12 | 0.39 |  | [View](https://fastrouter.ai/models/Qwen/Qwen2.5-72B-Instruct) |
| [Alibaba](/llm/alibaba.txt) | Qwen2.5 72B Instruct | 1.40 | 5.60 |  |  |
| [Abacus](/llm/abacus.txt) | Qwen 2.5 72B Instruct | 0.11 | 0.38 |  |  |
| [Alibaba (China)](/llm/alibabacn.txt) | Qwen2.5 72B Instruct | 0.57 | 1.72 |  |  |
| [Novita AI](/llm/novita.txt) | qwen-2.5-72b-instruct | 0.38 | 0.40 |  |  |
| [SiliconFlow (China)](/llm/siliconflowcn.txt) | Qwen/Qwen2.5-72B-Instruct | 0.59 | 0.59 |  |  |
| [SiliconFlow](/llm/siliconflow.txt) | Qwen2.5-72B-Instruct | 0.59 | 0.59 |  | [View](https://www.siliconflow.com./models/qwen2-5-72b-instruct) |
| [Nano-GPT](/llm/nanogpt.txt) | Qwen2.5 72B |  |  |  |  |
| [OpenRouter](/llm/openrouter.txt) | Qwen2.5 72B Instruct | 0.12 | 0.39 |  | [View](https://openrouter.ai/qwen/qwen-2.5-72b-instruct) |
| [Requesty](/llm/requesty.txt) |  | 0.38 | 0.40 |  |  |
| [Requesty](/llm/requesty.txt) |  | 0.23 | 0.40 |  |  |
| [Together AI](/llm/togetherai.txt) | Qwen2.5 72B Instruct | 1.20 | 1.20 |  |  |
| [ValorGPT](/llm/valorgpt.txt) | Qwen2.5 72B Instruct |  |  |  | [View](https://www.valorgpt.com/models/qwen-qwen-2.5-72b-instruct) |
| [Yupp](/llm/yupp.txt) | Qwen 2.5 72B Instruct (Chutes AI) |  |  |  |  |
| [Yupp](/llm/yupp.txt) | Qwen 2.5 72B Instruct (OpenRouter) |  |  |  |  |
| [DeepInfra](/llm/deepinfra.txt) | Qwen2.5-72B-Instruct | 0.12 | 0.39 |  |  |
| [LangDB](/llm/langdb.txt) | qwen-2.5-72b-instruct |  |  |  | [View](https://langdb.ai/app/models) |
| [Kilo Code](/llm/kilocode.txt) | Qwen2.5 72B Instruct | 0.12 | 0.39 |  |  |
| [Blackbox AI](/llm/blackboxai.txt) | Qwen2.5 72B Instruct | 0.12 | 0.39 |  |  |
| [NetMind](/llm/netmind.txt) | qwen2.5-72b-instruct | 0.50 | 0.70 |  |  |
| [CometAPI](/llm/cometapi.txt) |  | 3.20 | 3.20 |  |  |
| [ApiYI](/llm/apiyi.txt) | qwen2.5-72b-instruct |  |  |  |  |
| [WaveSpeed AI](/llm/wavespeed.txt) | qwen-2.5-72b-instruct | 0.13 | 0.43 |  |  |
| [Writingmate](/llm/writingmate.txt) | Qwen2.5 72B Instruct |  |  |  | [View](https://writingmate.ai/models/qwen/qwen-2.5-72b-instruct) |

---

[← Back to all providers](/llm.txt)