All tasks / Tools

Marker

Datalab's open-source PDF-to-Markdown/JSON converter running its Surya VLM locally; Datalab's hosted API runs Chandra.

  • Datalab
  • Local or cloud
  • Free, open source

Official site · Source code

Where it ranks

  • –
    Documents & OCR
    Parsers & APIs · Local · no rated model available here yet
    With cloud models: tier A (78 on OmniDocBench v1.6 (end-to-end, v1.6_full): pipeline tools)

Ranked by its own benchmark result where it has one; otherwise by the best model it offers.

Facts

Vendor
Datalab
Approach
Parsers & APIs
Where it runs
Runs fully on your hardware with local models; cloud models optional
Interface
Command line, API
Skill level
Advanced: command line, node graphs or self-hosting
Price
Free, open source
Pricing notes
Open-source code free; model weights free for research, personal use and startups under $5M funding/revenue. Datalab hosted API: Free plan (pay-as-you-go with a monthly allowance), Team $400/mo, Enterprise custom.
Source code
Open source (Apache-2.0 (code); model weights modified OpenRAIL-M)
GitHub stars
40.5k (18 Oct 2026)
Last verified
18 Oct 2026

Price from datalab.to, 18 Oct 2026.

Models it gives you

Its own benchmark results

BenchmarkResultEntry on the leaderboardAs ofSource
OmniDocBench v1.6 (end-to-end, v1.6_full): pipeline tools78Marker
Pipeline-tools row of the OmniDocBench v1.6_full end-to-end table; evaluated version 1.8.2 (current release 2.0.0).
11 Sep 2026github.com

Sources