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-vl | Unlimited OCRbaidu/unlimited-ocr | |
|---|---|---|
| Type | Open source | Open source |
| Price | 6 credits / page | 2 credits / page |
| Per 1,000 pages | $6.00 | $2.00 |
| Typical speed | 1.3 s / page | 1.2 s / page |
| Best for | CJK documents | Books and very long documents |
| Inputs | PDF, images | PDF, images |
| Languages | 109 languages | 30+ languages |
| Max pages per request | 500 | 1,000 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | ✓ Yes | No |
| Forms | No | No |
| Multilingual | ✓ Yes | ✓ Yes |
| On OCRRouter | Available | Available |
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-VL | Unlimited OCR | |
|---|---|---|
| Licence | Apache-2.0 | MIT |
| How you run it | Self-host only, via PaddleOCR, vLLM or transformers | Self-host with vLLM, SGLang or transformers, or use the hosted endpoint in Baidu Cloud's OCR product |
| Size | 0.9B parameters | 3B Mixture-of-Experts (Unlimited OCR 2 is 3.34B) |
| Output formats | Markdown, JSON | Markdown, plain text, bounding boxes |
| Multi-page input | Not published | 40+ pages in one pass, context capped at 32,768 tokens, multi-page only in base mode |
| Benchmark | 96.33 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 failure | Version 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 false | Repetition loops, hallucinated text, lost bold and italic styling, and version 2 runs out of memory on 12 GB GPUs under SGLang |
Sources
- PaddleOCR-VL-1.6 model card
- Issue #18088 Cyrillic regression
- Unlimited OCR Hugging Face model card
- MarkTechPost on Unlimited OCR 2
- Issue #116 OOM on 12 GB
What each one is
PaddleOCR-VL
Open-source document model from Baidu. Excellent on Chinese, Japanese and Korean.
PaddleOCR-VL detailsUnlimited OCR
Open-source model from Baidu that reads hundreds of pages in one pass with flat memory use.
Unlimited OCR detailsTry 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 vs MinerUPaddleOCR-VL vs GLM-OCRGLM-OCR vs Unlimited OCRQianfan OCR vs Unlimited OCRPaddleOCR-VL vs DoclingPaddleOCR-VL vs TesseractUnlimited OCR vs olmOCRUnlimited OCR vs RolmOCR
PaddleOCR-VL alternativesUnlimited OCR alternativesBest OCR models in 2026