# Marker

Document conversion project from Datalab for extracting Markdown and structured JSON from PDFs.

- Company: Datalab
- Category: Platforms & Infrastructure
- Business model: Open (open weights/source)
- Availability: unknown
- Launched: Not recorded
- Tags: parse, developer-tools
- Website: https://www.datalab.to/
- Documentation: https://github.com/datalab-to/marker
- Pricing page: https://www.datalab.to/pricing
- License: Not recorded
- Canonical URL: https://globalaiproductindex.com/products/marker/
- Record updated: 2026-11-03

Typical uses include Document ingestion for RAG; Extraction of structured document content. Documented capabilities: Convert PDF documents to Markdown and JSON; Preserve tables, images and document layout; Optional LLM-assisted correction during conversion.

## Key features

- Convert PDF documents to Markdown and JSON
- Preserve tables, images and document layout
- Optional LLM-assisted correction during conversion

## Use cases

- Document ingestion for RAG
- Extraction of structured document content

## Pricing

Marker code is Apache-2.0, but its model weights use modified AI Pubs Open Rail-M terms: research, personal use and businesses below USD 5 million funding/revenue qualify for free use; larger commercial use needs a license. Datalab’s hosted API is a separate metered service.

## FAQ

**Where does Marker fit in a workflow?**

Document conversion project from Datalab for extracting Markdown and structured JSON from PDFs. Convert PDF documents to Markdown and JSON.

**What costs and limits should I compare before choosing Marker?**

Marker code is Apache-2.0, but its model weights use modified AI Pubs Open Rail-M terms: research, personal use and businesses below USD 5 million funding/revenue qualify for free use; larger commercial use needs a license. Datalab’s hosted API is a separate metered service.

## Sources

- [Marker — official product](https://www.datalab.to/)
- [Marker — official documentation and terms](https://github.com/datalab-to/marker)
- [Marker — official documentation and terms](https://www.datalab.to/pricing)

---
Data from the [Global AI Product Index](https://globalaiproductindex.com/), licensed CC BY 4.0.