Unlimited OCR vs Nanonets-OCR
Pick Unlimited OCR for long reports and books, bulk PDF to text for RAG, and layout-aware extraction with bounding boxes. Pick Nanonets-OCR for printed business documents with signatures, watermarks and checkboxes, or flowcharts you want as Mermaid. The main split is scope: Unlimited OCR reads 40+ pages in one pass under an MIT licence, while Nanonets-OCR works on single page images and does not state a licence.
Unlimited OCRbaidu/unlimited-ocr | Nanonets-OCRnanonets/nanonets-ocr | |
|---|---|---|
| Type | Open source | Open source |
| Price | 2 credits / page | 2 credits / page |
| Per 1,000 pages | $2.00 | $2.00 |
| Typical speed | 1.2 s / page | 1.8 s / page |
| Best for | Books and very long documents | Markdown with semantic tags |
| Inputs | PDF, images | PDF, images |
| Languages | 30+ languages | Multilingual |
| Max pages per request | 1,000 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | ✓ Yes | No |
| Confidence | No | No |
| Forms | No | ✓ Yes |
| 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 Unlimited OCR if
- It parses 40+ pages in a single forward pass with roughly constant memory, so long reports and books go in as one request.
- It is MIT licensed, which allows commercial use with no copyleft.
- It returns block types and bounding boxes along with the text, which helps layout-aware extraction.
Choose Nanonets-OCR if
- It tags signatures, watermarks and image descriptions, and turns checkboxes into unicode symbols, which suits forms and business documents.
- It extracts flowcharts and org charts as Mermaid code, and separates inline from display LaTeX equations.
- It scores 89.43 on DocVQA and runs as a 3B model, with no CUDA version or 12 GB memory problem listed in its notes.
Key differences
| Unlimited OCR | Nanonets-OCR | |
|---|---|---|
| Licence | MIT | Not stated on the Nanonets-OCR2-3B model card; the base model is Qwen2.5-VL-3B |
| How you run it | Self-host with vLLM, SGLang or transformers, or use the hosted endpoint in Baidu Cloud's OCR product | Self-host the weights from Hugging Face; no hosted option listed |
| Output formats | Markdown, plain text, bounding boxes | Markdown, HTML, LaTeX, Mermaid |
| Document length | 40+ pages in one pass; context capped at 32,768 tokens, and multi-page input only works in base mode | Image to Markdown model; no multi-page mode published |
| Benchmarks | ParseBench mean 46.17 (independent); Unlimited OCR 2 scores 84.6 on MPDocBench and 77.1 on MarathonDocBench (authors) | olmOCR-bench overall 69.5, DocVQA 89.43, ChartQA 78.56 (authors, OCR2-3B) |
| Hardware | NVIDIA GPU with CUDA 12.9 or 13.0; version 2 under SGLang runs out of memory on 12 GB GPUs; no CPU-only | Not published |
| Known failures | Repetition loops, reported hallucinated text, mostly lost bold and italic styling (ParseBench text formatting 0.97), bbox coordinate loops on GB10 GPUs under SGLang | Not trained on handwriting and can hallucinate; fixed prompt, other prompts can hallucinate; handwriting test saw generation loops with CER up to 2100% |
Sources
- Hugging Face model card
- GitHub repo
- MarkTechPost on Unlimited OCR 2
- Nanonets-OCR2-3B model card
- Nanonets-OCR-s announcement
- HF discussion fixed prompt
What each one is
Unlimited OCR
Open-source model from Baidu that reads hundreds of pages in one pass with flat memory use.
Unlimited OCR detailsNanonets-OCR
Open image-to-Markdown model that tags tables, equations, signatures, watermarks and checkboxes.
Nanonets-OCR detailsTry both on your own file
Run the file once with each model and compare the output.
Use one, fall back to the other
{"model": "baidu/unlimited-ocr","fallbacks": ["nanonets/nanonets-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Unlimited OCR alternativesNanonets-OCR alternativesBest OCR models in 2026