Marker vs RapidOCR
Pick Marker when you need PDFs turned into Markdown, HTML or JSON, such as books, papers with equations or RAG chunks, and your company is under the weight license limit. Pick RapidOCR when you need plain text and boxes from Chinese or English images on CPU, or need OCR inside a Java, C# or C++ app under a plain Apache-2.0 licence. The main split is output: Marker returns structured documents, RapidOCR returns text lines and coordinates only.
Markerdatalab/marker | RapidOCRrapidai/rapidocr | |
|---|---|---|
| Type | OCR API | Open source |
| Price | 14 credits / page | 1 credit / page |
| Per 1,000 pages | $14.00 | $1.00 |
| Typical speed | 2.5 s / page | 0.6 s / page |
| Best for | Books and research papers | Lightweight OCR on CPU or edge |
| Inputs | PDF, images, DOCX | images |
| Languages | 90+ languages | Chinese, English and more |
| Max pages per request | 1,000 | 100 |
| Tables | ✓ Yes | No |
| Handwriting | No | No |
| Math | ✓ Yes | No |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | No | ✓ Yes |
| 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 Marker if
- You want PDF to Markdown, HTML, JSON block trees, LaTeX or RAG chunks rather than raw text.
- You work with books and papers that contain equations.
- You want a hosted option: Datalab's API includes about 5,000 free pages per month.
Choose RapidOCR if
- You need free commercial use with no revenue cap, since the code is Apache-2.0 (converted models keep their upstream licenses).
- You want to embed OCR from Python, C++, Java or C#, with engines such as ONNX Runtime, TensorRT, OpenVINO or MNN.
- You process Chinese and English screenshots or receipts offline on CPU.
Key differences
| Marker | RapidOCR | |
|---|---|---|
| Licence | Code is Apache-2.0. Model weights use a modified AI Pubs Open Rail-M license, free for research, personal use and startups under $5M. | Apache-2.0. Converted models keep their upstream licenses. |
| Output formats | Markdown, HTML, JSON, chunks, LaTeX, images. | Plain text and bounding boxes. |
| How you run it | Local on GPU, CPU or Apple Silicon (MPS), or Datalab's hosted API. | Local library for Python, C++, Java or C#. CPU through ONNX Runtime by default. |
| Price | Free self-hosted within the weight license. Hosted API has about 5,000 free pages per month, then paid plans. | Free, self-hosted. You pay for compute. |
| Benchmark | 83.7 on olmOCR-bench in vllm mode, 66.6 in CPU fast mode. These are Datalab's own numbers. | Not published |
| Languages | Not published | Chinese and English only by default. Other languages need extra models. |
| Known failure | Commercial use by companies above $5M needs a paid license. | 16-bit grayscale PNG or TIFF give no text or wrong text. Arabic recognition crashes without a manual fix. Sliced inference crashes on large pages. |
Sources
What each one is
Marker
Hosted version of the open-source Marker and Surya models. Strong on books and papers.
Marker detailsRapidOCR
PaddleOCR models packaged for ONNX Runtime and other engines. Easy to deploy without Paddle.
RapidOCR 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": "datalab/marker","fallbacks": ["rapidai/rapidocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Marker alternativesRapidOCR alternativesBest OCR models in 2026