# Qwen2.5 72B Instruct

> Qwen2.5 72B Instruct is an open-weight language model from Alibaba (Qwen), released on Sept 2024. It accepts text and generates text, with a 131K-token context window and up to 8K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.36 per million input tokens and $0.40 per million output tokens (OpenRouter), across 2 providers we track.

Source page: https://www.aimodel.directory/models/qwen2-5-72b-instruct
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Alibaba (Qwen)
- **Release date:** Sept 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen2-5-72b-instruct.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen2-5-72b-instruct.toml)
- **Weights:** Open weights (source: Hugging Face, https://huggingface.co/Qwen/Qwen2.5-72B-Instruct)
- **License:** qwen (source: Hugging Face, https://huggingface.co/Qwen/Qwen2.5-72B-Instruct)
- **Parameters:** 72.7B (source: Hugging Face, https://huggingface.co/Qwen/Qwen2.5-72B-Instruct)
- **Context window:** 131K (131,072 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen2-5-72b-instruct.toml)
- **Max output:** 8K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen2-5-72b-instruct.toml)
- **Knowledge cutoff:** Apr 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen2-5-72b-instruct.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen2-5-72b-instruct.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen2-5-72b-instruct.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen2-5-72b-instruct.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen2-5-72b-instruct.toml)
- **Hugging Face:** Qwen/Qwen2.5-72B-Instruct (source: Hugging Face, https://huggingface.co/Qwen/Qwen2.5-72B-Instruct)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| OpenRouter | $0.36 | $0.40 | – | 33K |
| Alibaba Cloud Model Studio | $1.40 | $5.60 | – | 131K |

## FAQ

### What is the context window of Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct has a context window of 131,072 tokens (131K) and can generate up to 8,192 tokens in a single response, according to models.dev.

### How much does the Qwen2.5 72B Instruct API cost?

Through Alibaba Cloud Model Studio, Qwen2.5 72B Instruct costs $1.40 per million input tokens and $5.60 per million output tokens. The lowest listed price is $0.36 input / $0.40 output through OpenRouter. Prices last verified 4 Oct 2026.

### Is Qwen2.5 72B Instruct open source?

Qwen2.5 72B Instruct is an open-weight model: its weights are published on Hugging Face as Qwen/Qwen2.5-72B-Instruct under the qwen license. Check the license terms before commercial use.

### When was Qwen2.5 72B Instruct released?

Alibaba (Qwen) released Qwen2.5 72B Instruct on Sept 2024, according to models.dev.

### Which providers offer Qwen2.5 72B Instruct?

We track Qwen2.5 72B Instruct on 2 providers: OpenRouter, Alibaba Cloud Model Studio.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Qwen2.5 72B Instruct", https://www.aimodel.directory/models/qwen2-5-72b-instruct