OCRRouter

Mistral OCR vs Marker

Pick Mistral OCR for high-volume, hosted PDF to Markdown, such as scanned business documents in batch for RAG, where the $2 per 1,000 pages price ($1 via Batch API) is the main draw. Pick Marker when you want to self-host, run on CPU or Apple Silicon, or convert books and papers with equations. Check Marker's weight license first if your company earns over $5M.

Mistral OCRmistral/mistral-ocrMarkerdatalab/marker
TypeOCR APIOCR API
Price25 credits / page14 credits / page
Per 1,000 pages$25.00$14.00
Typical speed0.9 s / page2.5 s / page
Best forHigh-volume PDF to MarkdownBooks and research papers
InputsPDF, imagesPDF, images, DOCX
Languages100+ languages90+ languages
Max pages per request1,0001,000
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
FormsNoNo
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 Mistral OCR if

  • It costs $2 per 1,000 pages, or $1 per 1,000 through the Batch API, with no hardware to run.
  • OCR 3 rebuilds tables as HTML with rowspan and colspan.
  • Mistral reports a 74% win rate for OCR 3 over OCR 2 on forms, scans, tables and handwriting.

Choose Marker if

  • You can run it locally on GPU, CPU or Apple Silicon, and you only pay for compute.
  • It outputs LaTeX, JSON block trees and RAG chunks, and suits books and papers with equations.
  • It has a fast mode that runs on CPU at 23.6 pages per second with about 18 MB of ONNX weights.

Key differences

Mistral OCRMarker
How you run itHosted API only.Self-hosted on GPU, CPU or MPS, or Datalab's hosted API.
LicenceProprietary.Code is Apache-2.0. Weights use a modified AI Pubs Open Rail-M license, free for research, personal use and startups under $5M.
Price$2 per 1,000 pages; $3 with structured annotations; $1 via Batch API.Free self-hosted within the weight license; hosted API has about 5,000 free pages per month, then paid plans.
Output formatsMarkdown, HTML, JSON, images.Markdown, HTML, JSON, chunks, LaTeX, images.
BenchmarkOmniDocBench v1.5 overall 78.83 (for the 2503 version) and v1.6 overall 85.66, both independent.olmOCR-bench 83.7 and OmniParseBench 85.9 in vllm mode, both reported by Datalab. CPU fast mode scores 66.6 on olmOCR-bench.
Known failureHallucinated text on unreadable handwriting; changed checkbox states and misread characters on a dense financial table page; colored-background pages returned as images in the 2025 release.CPU fast mode loses accuracy, and the weight license blocks free commercial use above $5M.
HardwareNone needed on your side.vllm mode needs an NVIDIA GPU; fast mode runs on CPU.

Sources

What each one is

Mistral OCR

Fast document OCR that returns clean Markdown with tables and embedded images.

Mistral OCR details

Marker

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

Marker 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": "mistral/mistral-ocr","fallbacks": ["datalab/marker"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Mistral OCR alternativesMarker alternativesBest OCR models in 2026