Marker
Convert PDFs to markdown and JSON with high-accuracy document intelligence models
- Also known as
- marker
What is Marker?
A tool that transforms PDFs into structured markdown and JSON formats using advanced machine learning models for layout analysis and optical character recognition. Supports integration with various language models including Claude, Gemini, and OpenAI-compatible APIs.
Marker pricing
Plans, per-tier features and add-ons, dated and linked to live pricing. Pricing changes often; always verify at source before you rely on it.
Free open source (research, personal, startups <$5M). Commercial licensing available.
Open Source
FreeFree for research, personal use, and startups under $5M funding/revenue
- PDF to markdown/JSON conversion
- Layout analysis with OCR
- Table recognition
- LLM integration support
Commercial
Contact salesCommercial use of model weights beyond startup threshold requires licensing
What Marker does
The capabilities that matter for ai data extraction agents, normalised so it lines up with every alternative. “-” means we haven't confirmed it, not that it's missing.
- Architecture model
- Open source library
- PDF and multimodal image OCR parsing
- ✓
- Web scraping to markdown or json
- ✓
- Tabular layout preservation for complex tables
- ✓
- Strict json schema forcing and validation
- -
- Fine tuned document layout analysis models
- ✓
- Native chunking and vectorization for rag
- -
- Javascript rendering for spa web scraping
- ✗
- Human in the loop hitl confidence review queue
- -
- Zero data retention privacy guarantees
- ✓
- SOC2 type ii
- -
- Mit or apache permissive oss license
- ✓
- Pricing model
- Free open source
Platform & deployment
Independently observed- CLI
- Self-hosted
Integrations (9)
Independently observed- Azure OpenAI←
- Google Vertex AI←
- Gemini
- Claude
- OpenAI
- Azure
- Vertex
- OpenRouter
- Ollama
Security & compliance
Known vulnerabilities: 0 (0 in the last 12 months) sourcea count reflects scale & disclosure, not quality
Marker FAQ
Common questions about Marker, answered from independent, dated evidence.
What is Marker?
An open-source tool that extracts text, tables, and layouts from PDF files with high accuracy. It offers multiple processing modes (fast, balanced, OCR) and optional integration with language models for enhanced formatting and content extraction. It is indexed under AI Data Extraction Agents.
Source: https://github.com/pricing
Is Marker free?
Marker offers a free tier, so you can start without paying. Pricing changes often, so verify at source before relying on it.
Source: https://github.com/pricing
What platforms does Marker support?
Marker supports a command-line interface. Platforms we have not confirmed are simply not listed here rather than ruled out.
Source: https://github.com/pricing
Can Marker be self-hosted?
Yes. Marker can be deployed self-hosted, so it does not have to run on the vendor's infrastructure.
Source: https://github.com/pricing
What does Marker integrate with?
We have confirmed 7 integrations for Marker, including Gemini, Claude, OpenAI, Azure, Vertex, OpenRouter and Ollama. This is what we could verify from public sources, so the vendor may support others we have not indexed.
Source: https://github.com/pricing
What security certifications does Marker have?
We have independently confirmed SOC 2 for Marker. Certifications we do not list are ones we have not been able to verify from public sources, which is not the same as Marker not holding them. Always confirm compliance directly before you rely on it.
Is Marker open source?
Yes. Marker is published under the Apache-2.0 licence, a permissive licence that generally allows commercial use and modification. Licence terms can change between releases, so verify against the repository for the version you intend to use.
Marker alternatives
Other ai data extraction agents we track, ranked by the same independent score.
- ReductoConvert unstructured documents into structured, machine-readable data using AImedium · 73%
- SensibleConvert documents into clean, structured data using AI paired with rule-based processing.medium · 73%
- KlippaAutomate administrative processes to free up time for core business activitieslow · 27%
- ZeroxConversational AI agents for financial institutions that automate borrower interactions across email, SMS, and voice channelslow · 10%
Compare Marker
Side by side against other ai data extraction agents, attribute by attribute, with a source on every value.
The vioscaleAI score: one lens on the evidence
Not user reviews and not a paid placement: a confidence-weighted blend of the independent signals below (adoption, activity, security posture, and more), which you can sort and re-weight yourself. Vendors can correct their listing but can never move their rank, and stars are weighted low as a vanity metric. It is one way to read the evidence for Marker, not the verdict.
| Signal | Score | Weight | Contribution | Evidence |
|---|---|---|---|---|
| Release cadence | 97 | 0.08 | 7.8 | ✓ |
| Capabilities | 81 | 0.08 | 6.5 | ✓ |
| Security posture | 40 | 0.12 | 4.9 | ✓ |
| Stars | 87 | 0.05 | 4.1 | ✓ |
| Development activity | 27 | 0.14 | 3.6 | ✓ |
| Integrations | 26 | 0.05 | 1.4 | ✓ |
| Dependent projects | 0 | 0.05 | 0.0 | ✓ |
| Package downloads | 0 | 0.04 | 0.0 | - |
| Security score | 0 | 0.05 | 0.0 | - |
| Developer Q&A activity | 0 | 0.14 | 0.0 | - |
Computed . Re-weight it by intent, or see the full method.
All data & sourcesshow ↓
Every value we hold, with its source, retrieval date, and confidence. This is the evidence behind the score: don't trust it, verify it.
Activity
| Attribute | Value | Evidence |
|---|---|---|
| Commits last 30d | 6 | mediumsource · 2026-09-14 · 65% |
Adoption
Content
| Attribute | Value | Evidence |
|---|---|---|
| Faq | 7 items | mediumsource · 2026-09-10 · 63% |
Features
| Attribute | Value | Evidence |
|---|---|---|
| Capabilities | Pricing model: free_open_source · Architecture model: open_source_library · Web scraping to markdown or json: Yes · Mit or apache permissive oss license: Yes · Pdf and multimodal image ocr parsing: Yes · Zero data retention privacy guarantees: Yes | mediumsource · 2026-10-14 · 60% |
Integrations
| Attribute | Value | Evidence |
|---|---|---|
| Count | 7 | mediumsource · 2026-10-14 · 60% |
Language
| Attribute | Value | Evidence |
|---|---|---|
| Primary | Python | highsource · 2026-10-14 · 90% |
License
| Attribute | Value | Evidence |
|---|---|---|
| Spdx | Apache-2.0 | highsource · 2026-10-14 · 95% |
Pricing
Release
Security
| Attribute | Value | Evidence |
|---|---|---|
| Soc2 | Yes | lowsource · 2026-10-14 · 48% |
| Vulnerabilities | Count: 0 · Source: https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=go&package_name=github.com%2FVikParuchuri%2Fmarker&per_page=100 · Last 12m: 0 | highsource · 2026-10-14 · 90% |
| Trust center | https://github.com/security | mediumsource · 2026-10-14 · 60% |
Is Marker the right choice for you?
Tell us the job, the constraints and what you weigh most, and we will rank Marker against the rest of the ai data extraction agents we index, using the same dated evidence weighted your way.
Free to run, no account needed to start. How the evaluation works
Is this your product?
This profile was built from public sources without asking you. You can take the badge below and use it anywhere, and you can claim the profile to correct anything we got wrong. Both are free, and neither moves Marker up or down: nobody can buy rank here, including you.
Take the badge
Live, always current, and free to use on your own site. It shows Marker's independent score and links back to this profile.
<a href="https://www.vioscale.ai/software/marker" target="_blank" rel="noopener">
<img src="https://www.vioscale.ai/badge/software/marker.svg" alt="Marker, verified on vioscaleAI" width="330" height="76" loading="lazy" />
</a>Markdown, for a README →
[](https://www.vioscale.ai/software/marker)Claim the profile
Verify you control the domain, then point us at the pages that state the facts about Marker and add your own description and media. Free, and it does not change the score.
- Correct anything wrong, with evidence
- Point our crawler at the pages that matter
- Write your own description and add media
Not the owner? How vendor profiles work