OCRRouter

Marker vs Chandra

Pick Marker for self-hosted PDF to Markdown on modest hardware, including CPU or Apple Silicon, and for books and papers with equations or RAG chunking. Pick Chandra for multilingual scans and documents with tables, forms and math when you have an NVIDIA GPU or will use the hosted API. Chandra scores higher on olmOCR-bench (85.8 vs 83.7), but it needs a GPU and can hallucinate on hard pages.

Markerdatalab/markerChandradatalab/chandra
TypeOCR APIOpen source
Price14 credits / page2 credits / page
Per 1,000 pages$14.00$2.00
Typical speed2.5 s / page2.0 s / page
Best forBooks and research papersComplex layouts and handwriting
InputsPDF, images, DOCXPDF, images
Languages90+ languages40+ languages
Max pages per request1,000500
Tables✓ Yes✓ Yes
HandwritingNo✓ Yes
Math✓ Yes✓ Yes
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
FormsNo✓ Yes
Multilingual✓ Yes✓ Yes
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

  • It runs on GPU, CPU or Apple Silicon, and fast mode needs only about 18 MB of ONNX weights on CPU.
  • Fast mode processes 23.6 pages per second on CPU, which suits bulk conversion without a GPU.
  • It outputs Markdown, HTML, JSON block trees, RAG chunks, LaTeX and images, and its free threshold for startups is under $5M.

Choose Chandra if

  • It scores 85.8 on olmOCR-bench, above Marker's 83.7 in vllm mode, and above dots.ocr 1.5 (83.9) and olmOCR 2 (82.4).
  • It averages 77.8% across 43 languages, against 67.6% for Gemini 2.5 Flash, so it fits multilingual scans.
  • It returns layout chunks with bounding boxes and labels per block, and the hosted API lists clear per-1,000-page prices of $1, $3 and $7.50.

Key differences

MarkerChandra
LicenceCode Apache-2.0; weights under a modified AI Pubs Open Rail-M licence, free for research, personal use and startups under $5MCode Apache-2.0; weights under modified OpenRAIL-M, free for research, personal use and companies under $2M funding or revenue
HardwareGPU, CPU or MPS; vllm mode needs an NVIDIA GPUSingle NVIDIA GPU via vLLM; benchmarked on one H100 80GB, with presets for A100, L40S and RTX 4090/5090
Hosted pricingAbout 5,000 free pages per month; paid plans on Datalab's pricing page$1 (fast), $3 (balanced) or $7.50 (accurate) per 1,000 pages; free tier of $20/month with a work email
Output formatsMarkdown, HTML, JSON, chunks, LaTeX, imagesMarkdown, HTML, JSON, bounding boxes
olmOCR-bench83.7 in vllm mode; 66.6 in CPU fast mode (Datalab's own numbers)85.8 for Chandra 2 (authors' numbers)
Speed23.6 pages per second in CPU fast modeAbout 1.44 pages per second on one H100 with vLLM; one reviewer measured 66 seconds per page on an RTX 4090 with the Hugging Face path
Known failureFast mode drops accuracy on olmOCR-bench to 66.6Token-loop hallucinations on 5-6 of about 60 Russian/Kazakh scans in GitHub issue #51; weak on Urdu (43.2%) and Sanskrit (51.1%); Old Scans category only 51.1

Sources

What each one is

Marker

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

Marker details

Chandra

Datalab's OCR model that keeps layout and handles forms, tables and handwriting.

Chandra 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": ["datalab/chandra"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Marker alternativesChandra alternativesBest OCR models in 2026