OCRRouter

PaddleOCR-VL vs Unlimited OCR

Pick PaddleOCR-VL for multilingual scans, formula-heavy papers and tables on a modest GPU. It is under 1B parameters and covers 109 languages. Pick Unlimited OCR for long reports and books, because it parses 40+ pages in one pass and returns bounding boxes.

PaddleOCR-VLpaddle/paddleocr-vlUnlimited OCRbaidu/unlimited-ocr
TypeOpen sourceOpen source
Price6 credits / page2 credits / page
Per 1,000 pages$6.00$2.00
Typical speed1.3 s / page1.2 s / page
Best forCJK documentsBooks and very long documents
InputsPDF, imagesPDF, images
Languages109 languages30+ languages
Max pages per request5001,000
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ Yes✓ Yes
Confidence✓ YesNo
FormsNoNo
Multilingual✓ Yes✓ Yes
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 PaddleOCR-VL if

  • It supports 109 languages, including Cyrillic, Arabic, Devanagari and Thai, in one model.
  • At 0.9B parameters it runs on much smaller GPUs than 3B or 7B document models.
  • It reads text, tables, formulas and charts, and outputs Markdown and JSON, which suits academic papers and reports.

Choose Unlimited OCR if

  • It parses 40+ pages in a single forward pass with roughly constant memory, so a whole book goes in one request.
  • It returns block types and bounding boxes with the text, which helps layout-aware extraction.
  • It is MIT licensed, and Baidu Cloud also offers a hosted endpoint if you do not want to run GPUs.

Key differences

PaddleOCR-VLUnlimited OCR
LicenceApache-2.0MIT
How you run itSelf-host only, via PaddleOCR, vLLM or transformersSelf-host with vLLM, SGLang or transformers, or use the hosted endpoint in Baidu Cloud's OCR product
Size0.9B parameters3B Mixture-of-Experts (Unlimited OCR 2 is 3.34B)
Output formatsMarkdown, JSONMarkdown, plain text, bounding boxes
Multi-page inputNot published40+ pages in one pass, context capped at 32,768 tokens, multi-page only in base mode
Benchmark96.33 on OmniDocBench v1.6 (authors); 80.0 on olmOCR-Bench (independent)46.17 on ParseBench mean (independent); 77.1 on MarathonDocBench for version 2 (authors)
Known failureVersion 1.6 regresses Russian and Kazakh Cyrillic on born-digital PDFs, hangs on blurry images, and decodes about 11x slower because use_cache ships as falseRepetition loops, hallucinated text, lost bold and italic styling, and version 2 runs out of memory on 12 GB GPUs under SGLang

Sources

What each one is

PaddleOCR-VL

Open-source document model from Baidu. Excellent on Chinese, Japanese and Korean.

PaddleOCR-VL details

Unlimited OCR

Open-source model from Baidu that reads hundreds of pages in one pass with flat memory use.

Unlimited OCR 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": "paddle/paddleocr-vl","fallbacks": ["baidu/unlimited-ocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

PaddleOCR-VL alternativesUnlimited OCR alternativesBest OCR models in 2026