OCRRouter

Qwen-VL vs Donut

Pick Qwen-VL if you want one Apache-2.0 model that reads photos, screenshots and documents and outputs Markdown, HTML, JSON or bounding boxes without training. Pick Donut if your documents are a narrow, fixed-layout type such as receipts or forms and you will fine-tune it to return JSON. The main split is that Qwen-VL works out of the box but can loop on low-quality scans, while Donut needs training before it is usable.

Qwen-VLqwen/qwen-vlDonutnaver/donut
TypeOpen sourceOpen source
Price2 credits / page1 credit / page
Per 1,000 pages$2.00$1.00
Typical speed2.0 s / page1.0 s / page
Best forFlexible extraction with promptsReceipt and form fields after fine-tuning
InputsPDF, imagesimages
Languages30+ languagesEnglish, Chinese, Japanese, Korean
Max pages per request200100
Tables✓ YesNo
Handwriting✓ YesNo
Math✓ YesNo
Bounding boxes✓ YesNo
ConfidenceNoNo
FormsNo✓ Yes
Multilingual✓ YesNo
On OCRRouterAvailableAvailable

Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.

Which to choose

Choose Qwen-VL if

  • It runs without fine-tuning and outputs plain text, HTML, bounding boxes, JSON and Markdown.
  • It does OCR in 32 languages and comes in sizes from 2B to 235B-A22B MoE, all under Apache-2.0, with a hosted API on Alibaba Cloud if you do not want to run GPUs.
  • It handles OCR plus reasoning or VQA in one model, and copes with photos and screenshots with text, including low light, blur and tilted text per Qwen.

Choose Donut if

  • It maps document images straight to structured JSON with no separate OCR step, which suits receipt and form field extraction once fine-tuned.
  • It is MIT licensed and loads in Hugging Face Transformers, with no hosted service tied to it.
  • A practitioner on Hacker News reports about 200 documents of fine-tuning can reach human-level accuracy on narrow data.

Key differences

Qwen-VLDonut
LicenceApache-2.0MIT
How you run itSelf-host the open weights, or use the hosted API on Alibaba CloudSelf-host only
Ready to useYes, general model with OCR and document parsingNo, the base checkpoint is pretrain-only and must be fine-tuned
Output formatsPlain text, HTML, bounding boxes, JSON, MarkdownJSON, plain text
Published benchmarkQwen 3 VL 8B scores 64.6 on olmOCR-bench in the Datalab table, below dedicated OCR modelsNot published
Known failureCan loop and repeat the same text, mostly on low-quality images and worse with greedy decoding; GGUF builds of Qwen2.5-VL-32B often loop on scanned documentsMisses tiny text in large images because of input resolution limits
Setup notesFP8 checkpoints need an H100-class GPU and CUDA 12+Transformers v5 dropped image-to-text pipeline support, so load the model directly or use v4

Sources

What each one is

Qwen-VL

Alibaba's open-weight vision language models (Qwen2.5-VL, Qwen3-VL). Strong general OCR and grounding.

Qwen-VL details

Donut

OCR-free document understanding model. Fine-tuned for receipts, forms and document Q&A.

Donut details

Try both on your own file

Run the file once with each model and compare the output.

PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?

Use one, fall back to the other

{"model": "qwen/qwen-vl","fallbacks": ["naver/donut"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Qwen-VL alternativesDonut alternativesBest OCR models in 2026