# Marker vs Zerox

**Leader by vioscaleAI score:** Marker

| Attribute | Marker | Zerox |
|---|---|---|
| **vioscaleAI score** | 49.4 (76% (high)) | 41.2 (10% (low)) |
| activity.commits_last_30d | 6 | - |
| adoption.dependent_repos | 0 | - |
| adoption.github_stars | 40,445 | - |
| content.faq | `[{"answer":"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","question":"What is Marker?","confidence":0.6},{"answer":"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","question":"Is Marker free?","confidence":0.6},{"answer":"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","question":"What platforms does Marker support?","confidence":0.6},{"answer":"Yes. Marker can be deployed self-hosted, so it does not have to run on the vendor's infrastructure.","source":"https://github.com/pricing","question":"Can Marker be self-hosted?","confidence":0.6},{"answer":"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","question":"What does Marker integrate with?","confidence":0.6},{"answer":"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.","source":"https://github.com/VikParuchuri/marker","question":"What security certifications does Marker have?","confidence":0.48},{"answer":"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.","source":"https://github.com/VikParuchuri/marker","question":"Is Marker open source?","confidence":0.95}]` | `[{"answer":"A platform enabling AI agents to automate borrower interactions and document collection for financial institutions. Agents integrate with core banking systems, CRMs, and loan platforms to handle workflows end-to-end while maintaining compliance and audit trails. It is indexed under AI Data Extraction Agents.","source":"https://getomni.ai","question":"What is Zerox?","confidence":0.6},{"answer":"We have confirmed browser-based access to Zerox. That is the extent of what we could verify from public sources, so it may well offer desktop or mobile clients we have not indexed.","source":"https://getomni.ai","question":"What platforms does Zerox support?","confidence":0.6},{"answer":"We have only confirmed a cloud / SaaS deployment for Zerox, so it appears to be vendor-hosted. If a self-hosted option exists we have not found it documented publicly.","source":"https://getomni.ai","question":"Can Zerox be self-hosted?","confidence":0.6}]` |
| deployment.options | `{"self_hosted":true}` | `{"cloud":true}` |
| description.long | 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. | A platform enabling AI agents to automate borrower interactions and document collection for financial institutions. Agents integrate with core banking systems, CRMs, and loan platforms to handle workflows end-to-end while maintaining compliance and audit trails. |
| features.capabilities | `{"pricing_model":"free_open_source","architecture_model":"open_source_library","web_scraping_to_markdown_or_json":true,"mit_or_apache_permissive_oss_license":true,"pdf_and_multimodal_image_ocr_parsing":true,"zero_data_retention_privacy_guarantees":true,"javascript_rendering_for_spa_web_scraping":false,"fine_tuned_document_layout_analysis_models":true,"tabular_layout_preservation_for_complex_tables":true}` | `{"architecture_model":"managed_cloud_api","human_in_the_loop_hitl_confidence_review_queue":true}` |
| integrations.count | 7 | 1 |
| integrations.list | `[{"name":"Gemini"},{"name":"Claude"},{"name":"OpenAI"},{"name":"Azure"},{"name":"Vertex"},{"name":"OpenRouter"},{"name":"Ollama"},{"name":"Azure OpenAI","native":false,"category":"llm","direction":"inbound"},{"name":"Google Vertex AI","native":false,"category":"llm","direction":"inbound"}]` | `[{"name":"WhatsApp"}]` |
| language.primary | Python | - |
| license.spdx | Apache-2.0 | - |
| platform.support | `{"cli":true}` | `{"web":true}` |
| pricing | `{"type":"open_source","plans":[{"free":true,"name":"Open Source","features":["PDF to markdown/JSON conversion","Layout analysis with OCR","Table recognition","LLM integration support"],"description":"Free for research, personal use, and startups under $5M funding/revenue","contactSales":false},{"free":false,"name":"Commercial","description":"Commercial use of model weights beyond startup threshold requires licensing","contactSales":true}],"summary":"Free open source (research, personal, startups <$5M). Commercial licensing available.","freeTier":true,"sourceUrl":"https://github.com/pricing","retrievedAt":"2026-10-14T22:33:59.878Z"}` | - |
| pricing.free_tier | yes | - |
| pricing.model | open_source | - |
| pricing.price_level | free | - |
| pricing.transparent | yes | - |
| release.cadence_days | 6 | - |
| release.history | `[{"url":"https://github.com/datalab-to/marker/releases/tag/v2.0.0","date":"2026-07-20T19:41:39Z","type":"stable","version":"v2.0.0"},{"url":"https://github.com/datalab-to/marker/releases/tag/v1.10.2","date":"2026-01-31T00:12:04Z","type":"stable","version":"v1.10.2"},{"url":"https://github.com/datalab-to/marker/releases/tag/v1.10.1","date":"2025-09-30T15:40:24Z","type":"stable","version":"v1.10.1"},{"url":"https://github.com/datalab-to/marker/releases/tag/v1.10.0","date":"2025-09-24T01:19:13Z","type":"stable","version":"v1.10.0"},{"url":"https://github.com/datalab-to/marker/releases/tag/v1.9.3","date":"2025-09-09T20:43:45Z","type":"stable","version":"v1.9.3"},{"url":"https://github.com/datalab-to/marker/releases/tag/v1.9.2","date":"2025-09-04T18:47:56Z","type":"stable","version":"v1.9.2"},{"url":"https://github.com/datalab-to/marker/releases/tag/v1.9.1","date":"2025-09-02T14:39:45Z","type":"stable","version":"v1.9.1"},{"url":"https://github.com/datalab-to/marker/releases/tag/v1.9.0","date":"2025-08-29T23:03:17Z","type":"stable","version":"v1.9.0"},{"url":"https://github.com/datalab-to/marker/releases/tag/v1.8.5","date":"2025-08-23T17:09:33Z","type":"stable","version":"v1.8.5"},{"url":"https://github.com/datalab-to/marker/releases/tag/v1.8.4","date":"2025-08-20T16:47:03Z","type":"stable","version":"v1.8.4"},{"url":"https://github.com/datalab-to/marker/releases/tag/v1.8.3","date":"2025-08-04T18:16:49Z","type":"stable","version":"v1.8.3"},{"url":"https://github.com/datalab-to/marker/releases/tag/v1.8.2","date":"2025-07-15T18:26:09Z","type":"stable","version":"v1.8.2"},{"url":"https://github.com/datalab-to/marker/releases/tag/v1.8.1","date":"2025-07-04T18:45:30Z","type":"stable","version":"v1.8.1"},{"url":"https://github.com/datalab-to/marker/releases/tag/v1.8.0","date":"2025-06-27T19:55:09Z","type":"stable","version":"v1.8.0"},{"url":"https://github.com/datalab-to/marker/releases/tag/v1.7.5","date":"2025-06-11T20:36:33Z","type":"stable","version":"v1.7.5"},{"url":"https://github.com/datalab-to/marker/releases/tag/v1.7.4","date":"2025-06-02T23:11:13Z","type":"stable","version":"v1.7.4"},{"url":"https://github.com/datalab-to/marker/releases/tag/v1.7.3","date":"2025-05-22T19:41:35Z","type":"stable","version":"v1.7.3"},{"url":"https://github.com/datalab-to/marker/releases/tag/v1.7.2","date":"2025-05-20T16:47:48Z","type":"stable","version":"v1.7.2"},{"url":"https://github.com/datalab-to/marker/releases/tag/v1.7.1","date":"2025-05-19T22:50:02Z","type":"stable","version":"v1.7.1"},{"url":"https://github.com/datalab-to/marker/releases/tag/v1.7.0","date":"2025-05-19T21:07:30Z","type":"stable","version":"v1.7.0"}]` | - |
| security.soc2 | yes | - |
| security.trust_center | https://github.com/security | - |
| security.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,"max_severity":null}` | - |

## Capabilities (AI Data Extraction Agents)

| Capability | Marker | Zerox |
|---|:--:|:--:|
| **Capabilities** |  |  |
| Architecture model | Open source library | Managed cloud API |
| 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 | - |

*Source: vioscaleAI. Generated 2026-10-16T01:06:40.498Z. "-" = undocumented, not absent.*