Marker vs Typhoon OCR
Pick Marker for self-hosted PDF to Markdown on English documents such as books and papers with equations, or when you need JSON block trees and RAG chunks. Pick Typhoon OCR for Thai and Thai-English documents such as government forms and financial reports. The main split is language focus: Typhoon OCR is built for Thai and English only, while Marker is a general PDF converter whose weights restrict commercial use for companies above $5M.
Markerdatalab/marker | Typhoon OCRtyphoon/typhoon-ocr | |
|---|---|---|
| Type | OCR API | Open source |
| Price | 14 credits / page | 2 credits / page |
| Per 1,000 pages | $14.00 | $2.00 |
| Typical speed | 2.5 s / page | 1.8 s / page |
| Best for | Books and research papers | Thai documents |
| Inputs | PDF, images, DOCX | PDF, images |
| Languages | 90+ languages | Thai, English |
| Max pages per request | 1,000 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | No |
| Bounding boxes | ✓ Yes | No |
| Confidence | No | 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 Marker if
- You need a self-hosted converter that runs on GPU, CPU or Apple Silicon, with a CPU fast mode of about 18 MB of ONNX weights running at 23.6 pages per second.
- You want structured output beyond text: Markdown, HTML, JSON block trees, RAG chunks, LaTeX and images.
- You work with books and papers with equations, and you are a researcher, individual or startup under $5M, so the weight license is free for you.
Choose Typhoon OCR if
- Your documents are Thai or Thai-English, such as government forms, financial reports and books; V1.5 beat GPT-5 and Gemini 2.5 Pro on Thai government forms (BLEU 0.870).
- You want a small model: V2 is 2B parameters with a 0.8B variant, and it scores 84.7 on olmOCR-bench.
- You need tables as HTML with merged cells, equations as LaTeX and checkboxes marked, under Apache-2.0 subject to OpenTyphoon Terms and Conditions.
Key differences
| Marker | Typhoon OCR | |
|---|---|---|
| Licence | Code Apache-2.0; weights under a modified AI Pubs Open Rail-M license, free for research, personal use and startups under $5M. | Apache-2.0, subject to OpenTyphoon Terms and Conditions. |
| How you run it | Local on GPU, CPU or MPS; vllm mode needs an NVIDIA GPU. Datalab also sells a hosted API. | Self-hosted weights, or the Typhoon API as typhoon-ocr-v2. |
| Price | Free self-hosted within the weight license. Hosted API includes about 5,000 free pages per month. | Free self-hosted (you pay for compute). API pricing is not published on the model card. |
| Output formats | Markdown, HTML, JSON, chunks, LaTeX, images. | Markdown, HTML, LaTeX. |
| olmOCR-bench | 83.7 in vllm mode, 66.6 in CPU fast mode. Reported by Datalab. | 84.7 for V2 2B. Reported by the authors. |
| Languages | Not published | Only Thai and English evaluated. |
| Known failure | CPU fast mode drops to 66.6 on olmOCR-bench; commercial use blocked above $5M without a paid license. | V2 can loop until the token limit on dense multi-column pages; key-information extraction is weakest at 21.0 on ThaiOCRBench. |
Sources
What each one is
Marker
Hosted version of the open-source Marker and Surya models. Strong on books and papers.
Marker detailsTyphoon OCR
Open vision model tuned for Thai and English documents, with Markdown output.
Typhoon 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": "datalab/marker","fallbacks": ["typhoon/typhoon-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Marker alternativesTyphoon OCR alternativesBest OCR models in 2026