Unlimited OCR vs GOT-OCR 2.0
Pick Unlimited OCR to parse long reports and books in one request, with block types and bounding boxes under an MIT licence. Pick GOT-OCR 2.0 for formulas, sheet music and chemical structures, or when you need to OCR a specific region. The main split is scope: Unlimited OCR is built for 40+ page documents, while GOT-OCR 2.0 is a 580M model that reads many content types.
Unlimited OCRbaidu/unlimited-ocr | GOT-OCR 2.0stepfun/got-ocr-2 | |
|---|---|---|
| Type | Open source | Open source |
| Price | 2 credits / page | 1 credit / page |
| Per 1,000 pages | $2.00 | $1.00 |
| Typical speed | 1.2 s / page | 1.5 s / page |
| Best for | Books and very long documents | Formatted text, formulas and charts |
| Inputs | PDF, images | images |
| Languages | 30+ languages | Chinese, English |
| Max pages per request | 1,000 | 100 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | No |
| 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 you can send a long report or book in one request.
- It returns Markdown, plain text and bounding boxes, with block types alongside the text, which suits layout-aware extraction and bulk PDF to text for RAG.
- The MIT licence allows commercial use with no copyleft, and Baidu Cloud offers a hosted endpoint if you do not want to run GPUs.
Choose GOT-OCR 2.0 if
- It reads formulas, tables, charts, sheet music and geometry, and outputs LaTeX, TikZ, SMILES and kern, which Unlimited OCR does not list.
- It supports region OCR guided by box coordinates or color, so you can read one part of a page.
- At 580M parameters it is a much smaller model, and it is merged into Hugging Face Transformers with batched inference.
Key differences
| Unlimited OCR | GOT-OCR 2.0 | |
|---|---|---|
| Main job | Long multi-page documents parsed in one pass (40+ pages) | Text, formulas, tables, charts, sheet music and geometry |
| Licence | MIT | Code Apache-2.0; training data CC BY-NC 4.0 |
| How you run it | Self-host with vLLM, SGLang or transformers; hosted option in Baidu Cloud | Self-host only, via Hugging Face Transformers |
| Output formats | Markdown, plain text, bounding boxes | Plain text, Markdown, LaTeX, TikZ, SMILES, kern |
| Size and hardware | 3B total, about 500M active per token; NVIDIA GPU with CUDA 12.9 or 13.0; version 2 runs out of memory on 12 GB GPUs under SGLang | 580M; CUDA 11.8 and PyTorch 2.0.1 per README; CPU users are pointed to a llama.cpp port |
| Benchmarks | ParseBench mean 46.17; Unlimited OCR 2 scores 77.1 on MarathonDocBench and 84.6 on MPDocBench (author-reported) | Not published |
| Known failures | Text looping (issue #55), hallucinated text (issue #58), little bold or italic formatting kept, context capped at 32,768 tokens | Character looping (issue #226), wrong text on blank images (issue #235), format mode much worse than plain mode (issue #317) |
Sources
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 detailsGOT-OCR 2.0
Unified OCR model that reads plain text, tables, formulas, sheet music and charts.
GOT-OCR 2.0 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": ["stepfun/got-ocr-2"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Unlimited OCR alternativesGOT-OCR 2.0 alternativesBest OCR models in 2026