OCRRouter

Marker vs DeepSeek-VL2

Pick Marker to convert whole PDFs, such as books and papers with equations, into Markdown, HTML or JSON on your own hardware, and to chunk them for RAG. Pick DeepSeek-VL2 to answer questions about a single page or chart, where it scores 93.3 on DocVQA, and when its weights licence allows commercial use. The main split is the job: Marker is a PDF converter, DeepSeek-VL2 is a vision language model.

Markerdatalab/markerDeepSeek-VL2deepseek/deepseek-vl2
TypeOCR APIVision model
Price14 credits / page2 credits / page
Per 1,000 pages$14.00$2.00
Typical speed2.5 s / page3.0 s / page
Best forBooks and research papersCharts and tables
InputsPDF, images, DOCXimages
Languages90+ languagesMainly English and Chinese
Max pages per request1,000500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ YesNo
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
FormsNoNo
Multilingual✓ YesNo
On OCRRouterAvailableAvailable

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 or RAG chunks, plus LaTeX output for equations.
  • You have no big GPU: fast mode runs on CPU at 23.6 pages per second with about 18 MB of ONNX weights, though it drops to 66.6 on olmOCR-bench.
  • You want a hosted option too, since Datalab's API includes about 5,000 free pages per month.

Choose DeepSeek-VL2 if

  • You need to answer questions about documents and charts, with DocVQA 93.3 and ChartQA 86.0 for the full model.
  • Your company is above $5M and needs commercial use without a paid weight licence, since the DeepSeek Model License allows it.
  • You work one page at a time and can give it a GPU: Tiny runs under 40GB, and Small scores 834 on OCRBench.

Key differences

MarkerDeepSeek-VL2
What it isPDF to Markdown converter built on the Surya OCR modelsMixture-of-experts vision language model in Tiny, Small and full sizes
LicenceCode Apache-2.0; weights under a modified AI Pubs Open Rail-M licence, free for research, personal use and startups under $5MMIT for code; DeepSeek Model License for weights, commercial use allowed
How you run itSelf-host on GPU, CPU or Apple Silicon, or use Datalab's hosted APISelf-host the open weights only
HardwareCPU fast mode with about 18 MB of ONNX weights; vllm mode needs an NVIDIA GPUSmall may need 80GB GPU memory, or 40GB with incremental prefilling; Tiny runs under 40GB
Output formatsMarkdown, HTML, JSON, chunks, LaTeX, imagesPlain text, Markdown
BenchmarksolmOCR-bench 83.7 and OmniParseBench 85.9 in vllm mode, both reported by DatalabDocVQA 93.3, OCRBench 834 (Small), ChartQA 86.0, all from the authors' paper
Known failureCPU fast mode drops to 66.6 on olmOCR-benchStruggles with blurry images; supports only a few images per session, and dynamic tiling turns off with more than two images

Sources

What each one is

Marker

Hosted version of the open-source Marker and Surya models. Strong on books and papers.

Marker details

DeepSeek-VL2

DeepSeek's mixture-of-experts vision models (December 2024) with OCR and table and chart understanding.

DeepSeek-VL2 details

Try both on your own file

Run the file once with each model and compare the output.

PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?

Use one, fall back to the other

{"model": "datalab/marker","fallbacks": ["deepseek/deepseek-vl2"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Marker alternativesDeepSeek-VL2 alternativesBest OCR models in 2026