# Qwen2.5 VL 72B Instruct

Qwen2.5 VL 72B Instruct is a model from Alibaba with open weights, first recorded on 30 Sep 2026; its release date is not established. The context window is 128,000 tokens. Pricing is $0.80 per million input tokens and $1.00 per million output tokens.

- Developer: Alibaba
- Id: Qwen/Qwen2.5-VL-72B-Instruct
- Sighting: 2026-09-30T16:05:07.679Z
  - [evidence link](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct)
- Status: Released
- Weights version: 2025-01-27
  - [evidence link](https://huggingface.co/api/models/Qwen/Qwen2.5-VL-72B-Instruct/paths-info/89c86200743eec961a297729e7990e8f2ddbc4c5)
- Canonical: https://alexgetman.com/models/alibaba/qwen2-5-vl-72b-instruct/

## Questions

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

The context window is 128,000 tokens.

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

Pricing is $0.80 per million input tokens and $1.00 per million output tokens. Cached input is $0.40 per million.

### Are the weights of Qwen2.5 VL 72B Instruct publicly available?

Yes. Alibaba publishes the weights.

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

Its release date is not established. Signal Forge first recorded it on 30 Sep 2026.

## Evidence links

- [huggingface-router](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct)
- [hf-author-artifacts:Qwen](https://huggingface.co/api/models/Qwen/Qwen2.5-VL-72B-Instruct/paths-info/89c86200743eec961a297729e7990e8f2ddbc4c5)
- [openrouter](https://openrouter.ai/qwen/qwen2.5-vl-72b-instruct)

## Signals