Nanonets-OCR vs GOT-OCR 2.0
Pick Nanonets-OCR for printed business documents that you want as Markdown for an LLM, especially pages with signatures, watermarks, checkboxes or flowcharts. Pick GOT-OCR 2.0 for formulas, sheet music, chemical structures or region-specific OCR, and when you need a small 580M model. The main split is output: Nanonets tags document elements and emits Mermaid, while GOT-OCR 2.0 reads many specialised content types.
Nanonets-OCRnanonets/nanonets-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 | 1.8 s / page | 1.5 s / page |
| Best for | Markdown with semantic tags | Formatted text, formulas and charts |
| Inputs | PDF, images | images |
| Languages | Multilingual | Chinese, English |
| Max pages per request | 500 | 100 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | No | ✓ Yes |
| Confidence | No | No |
| Forms | ✓ Yes | 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 Nanonets-OCR if
- It tags signatures, watermarks and image descriptions, and converts checkboxes to unicode symbols.
- It extracts flowcharts and org charts as Mermaid code.
- It scores 89.43 on DocVQA and 69.5 on olmOCR-bench overall (OCR2-3B, reported by the authors), while GOT-OCR 2.0 publishes no benchmark scores.
Choose GOT-OCR 2.0 if
- It reads formulas, sheet music, chemical structures (SMILES) and geometry, with outputs such as LaTeX, TikZ and kern.
- It supports region OCR guided by box coordinates or color, plus multi-page OCR with dynamic resolution.
- At 580M parameters it is a much smaller model than Nanonets-OCR's 3B, and it is merged into Hugging Face Transformers with batched inference.
Key differences
| Nanonets-OCR | GOT-OCR 2.0 | |
|---|---|---|
| Model size | 3B (Hugging Face lists ~4B), fine-tuned from Qwen2.5-VL-3B | 580M |
| Licence | Not stated on the Nanonets-OCR2-3B model card; base model is Qwen2.5-VL-3B | Code Apache-2.0; data CC BY-NC 4.0 |
| Output formats | Markdown, HTML, LaTeX, Mermaid | Plain text, Markdown, LaTeX, TikZ, SMILES, kern |
| Published benchmarks | olmOCR-bench 69.5, DocVQA 89.43, ChartQA 78.56 (OCR2-3B, by the authors) | Not published |
| Handwriting | Not trained on handwriting and can hallucinate; one handwriting test saw generation loops with CER up to 2100% | Not published |
| Prompting and regions | Trained on a fixed prompt; other prompts are expected to hallucinate | Region OCR by box coordinates or color |
| Known failure | Loses to Gemini 2.5 Flash in 52.43% of head-to-head Markdown comparisons, wins 39.98% | Loops characters midway (issue #226), invents text on blank images (issue #235), and format mode is much worse than plain mode (issue #317) |
Sources
- Nanonets-OCR2-3B model card
- Nanonets-OCR-s announcement
- HF discussion fixed prompt
- GOT-OCR2.0 GitHub
- GOT-OCR 2.0 paper
- GitHub issue index
What each one is
Nanonets-OCR
Open image-to-Markdown model that tags tables, equations, signatures, watermarks and checkboxes.
Nanonets-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": "nanonets/nanonets-ocr","fallbacks": ["stepfun/got-ocr-2"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Nanonets-OCR alternativesGOT-OCR 2.0 alternativesBest OCR models in 2026