# Qwen-VL OCR

> Qwen-VL OCR is a proprietary language model from Alibaba (Qwen), released on 28 Oct 2024. It accepts text and images and generates text, with a 34K-token context window and up to 4K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.72 per million input tokens and $0.72 per million output tokens (Alibaba Cloud Model Studio), across 1 provider we track.

Source page: https://www.aimodel.directory/models/qwen-vl-ocr
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Alibaba (Qwen)
- **Release date:** 28 Oct 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen-vl-ocr.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen-vl-ocr.toml)
- **Weights:** Proprietary (API only) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen-vl-ocr.toml)
- **Context window:** 34K (34,096 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen-vl-ocr.toml)
- **Max output:** 4K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen-vl-ocr.toml)
- **Knowledge cutoff:** Apr 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen-vl-ocr.toml)
- **Input:** Text and images (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen-vl-ocr.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen-vl-ocr.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen-vl-ocr.toml)
- **Tool calling:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen-vl-ocr.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Alibaba Cloud Model Studio | $0.72 | $0.72 | – | 34K |

## FAQ

### What is the context window of Qwen-VL OCR?

Qwen-VL OCR has a context window of 34,096 tokens (34K) and can generate up to 4,096 tokens in a single response, according to models.dev.

### How much does the Qwen-VL OCR API cost?

Through Alibaba Cloud Model Studio, Qwen-VL OCR costs $0.72 per million input tokens and $0.72 per million output tokens. Prices last verified 4 Oct 2026.

### Is Qwen-VL OCR open source?

No. Qwen-VL OCR is a proprietary model; Alibaba (Qwen) has not released its weights. It is available through APIs including Alibaba Cloud Model Studio.

### When was Qwen-VL OCR released?

Alibaba (Qwen) released Qwen-VL OCR on 28 Oct 2024, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Qwen-VL OCR", https://www.aimodel.directory/models/qwen-vl-ocr