# Docling vs Unstructured

**Leader by vioscaleAI score:** Unstructured

| Attribute | Docling | Unstructured |
|---|---|---|
| **vioscaleAI score** | 58.4 (32% (low)) | 75.4 (53% (medium)) |
| activity.commits_last_30d | 100 | - |
| adoption.dependent_repos | 0 | - |
| adoption.github_stars | 68,824 | - |
| content.faq | `[{"answer":"A Python library that converts documents from multiple formats (PDF, Word, Excel, images, audio, video, etc.) into structured data representations. Offers sophisticated PDF analysis capabilities for layout, tables, and content extraction, plus OCR support and AI framework integration. It is indexed under Document AI.","source":"https://docling-project.github.io/docling/","question":"What is Docling?","confidence":0.6},{"answer":"Docling is open source, so it can be self-hosted and used at no licence cost. It is released under the MIT licence. Pricing changes often, so verify at source before relying on it.","source":"https://docling-project.github.io/docling/","question":"Is Docling free to use?","confidence":0.6},{"answer":"Docling supports the web, Windows, macOS, Linux and a command-line interface. Platforms we have not confirmed are simply not listed here rather than ruled out.","source":"https://docling-project.github.io/docling/","question":"What platforms does Docling support?","confidence":0.6},{"answer":"Yes. Docling can be deployed cloud / SaaS, on-premise, air-gapped and self-hosted, so it does not have to run on the vendor's infrastructure.","source":"https://docling-project.github.io/docling/","question":"Can Docling be self-hosted?","confidence":0.6},{"answer":"We have confirmed 6 integrations for Docling, including LangChain, LlamaIndex, Crew AI, Haystack, OpenContracts and Apify. This is what we could verify from public sources, so the vendor may support others we have not indexed.","source":"https://docling-project.github.io/docling/","question":"What does Docling integrate with?","confidence":0.6},{"answer":"Yes. Docling is published under the MIT 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/docling-project/docling","question":"Is Docling open source?","confidence":0.95}]` | `[{"answer":"An ETL platform that automatically transforms complex, unstructured documents and data into structured formats suitable for GenAI applications, supporting 65+ file types with built-in enrichment and embedding capabilities. It is indexed under Document AI.","source":"https://unstructured.io/pricing","question":"What is Unstructured?","confidence":0.6},{"answer":"Unstructured offers a free tier, so you can start without paying. Paid plans start at $0.01. Prices are published openly on the vendor's own pricing page. Pricing changes often, so verify at source before relying on it.","source":"https://unstructured.io/pricing","question":"Is Unstructured free?","confidence":0.6},{"answer":"Unstructured supports the web and a command-line interface. Platforms we have not confirmed are simply not listed here rather than ruled out.","source":"https://unstructured.io/pricing","question":"What platforms does Unstructured support?","confidence":0.6},{"answer":"Yes. Unstructured can be deployed cloud / SaaS, hybrid, on-premise and self-hosted, so it does not have to run on the vendor's infrastructure.","source":"https://unstructured.io/pricing","question":"Can Unstructured be self-hosted?","confidence":0.6},{"answer":"We have confirmed 40 integrations for Unstructured, including Airtable, Google Cloud Storage, Google Drive, Jira, PostgreSQL, S3, Salesforce and SFTP, plus 32 more. This is what we could verify from public sources, so the vendor may support others we have not indexed.","source":"https://unstructured.io/pricing","question":"What does Unstructured integrate with?","confidence":0.6},{"answer":"We have independently confirmed SOC 2, ISO 27001, HIPAA and GDPR for Unstructured. Certifications we do not list are ones we have not been able to verify from public sources, which is not the same as Unstructured not holding them. Always confirm compliance directly before you rely on it.","source":"https://unstructured.io/pricing","question":"What security certifications does Unstructured have?","confidence":0.6},{"answer":"Unstructured is available worldwide. Its primary market is the United States.","source":"https://unstructured.io/pricing","question":"Where is Unstructured available?","confidence":0.5}]` |
| deployment.options | `{"cloud":true,"air_gapped":true,"self_hosted":true}` | `{"cloud":true}` |
| description.long | A document processing platform that transforms diverse document formats into structured representations with detailed understanding of layout, structure, and content. It supports integration with AI systems and provides both cloud-based and local processing options. | A platform that processes PDFs, scans, images, and other document formats using AI to extract and organize their content into structured formats for language models. Offers open-source libraries and a metered-usage cloud API. |
| features.capabilities | `{"open_source":true,"pricing_model":"free_open_source","prebuilt_models":true,"table_extraction":true,"architecture_model":"open_source_library","llm_vlm_based_extraction":true,"mit_or_apache_permissive_oss_license":true,"pdf_and_multimodal_image_ocr_parsing":true,"zero_data_retention_privacy_guarantees":true,"native_chunking_and_vectorization_for_rag":true,"fine_tuned_document_layout_analysis_models":true,"tabular_layout_preservation_for_complex_tables":true}` | `{"open_source":true,"soc2_type_ii":true,"pricing_model":"pay_per_page_api","prebuilt_models":true,"table_extraction":true,"architecture_model":"managed_cloud_api","confidence_scoring":false,"id_document_parsing":false,"rpa_erp_integration":false,"custom_model_training":true,"handwriting_recognition":false,"human_in_the_loop_review":false,"llm_vlm_based_extraction":true,"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,"native_chunking_and_vectorization_for_rag":true,"strict_json_schema_forcing_and_validation":false,"fine_tuned_document_layout_analysis_models":true,"human_in_the_loop_hitl_confidence_review_queue":false,"tabular_layout_preservation_for_complex_tables":true}` |
| integrations.count | 1 | 40 |
| integrations.list | `[{"name":"LangChain"},{"name":"LlamaIndex"},{"name":"Crew AI"},{"name":"Haystack"},{"name":"OpenContracts"},{"name":"Apify"},{"name":"Label Studio"},{"name":"Semantica","native":true,"category":"knowledge_graph","direction":"outbound"}]` | `[{"name":"Airtable"},{"name":"Google Cloud Storage"},{"name":"Google Drive"},{"name":"Jira"},{"name":"PostgreSQL"},{"name":"S3"},{"name":"Salesforce"},{"name":"SFTP"},{"name":"Slack"},{"name":"Snowflake"},{"name":"SQLite"},{"name":"Zendesk"},{"name":"Amazon Bedrock"},{"name":"Astra DB"},{"name":"DuckDB"},{"name":"Elasticsearch"},{"name":"IBM Milvus"},{"name":"IBM watsonx.data"},{"name":"Weaviate"},{"name":"OpenAI"},{"name":"Anthropic"},{"name":"Azure OpenAI"},{"name":"Google Gemini"},{"name":"AWS Bedrock"},{"name":"IBM watsonx"},{"name":"NVIDIA"},{"name":"Together.ai"},{"name":"VertexAI"},{"name":"Cohere"},{"name":"Amazon S3"},{"name":"Azure Blob Storage"},{"name":"Databricks"},{"name":"OpenSearch"},{"name":"Neo4j"},{"name":"Kafka"},{"name":"Box"},{"name":"OneDrive"},{"name":"Confluence"},{"name":"Dropbox"},{"name":"LangChain"},{"name":"SAP"},{"name":"Teradata"},{"name":"Cursor"},{"name":"Codex"},{"name":"Gemini","native":true,"category":"llm","direction":"outbound"}]` |
| language.primary | Python | - |
| license.spdx | MIT | - |
| market.availability | `{"primaryMarkets":[],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` | `{"primaryMarkets":["US"],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` |
| platform.support | `{"cli":true,"web":true}` | `{"web":true}` |
| pricing | `{"type":"open_source","summary":"Open source project, free to use","freeTier":true,"sourceUrl":"https://docling-project.github.io/docling/","retrievedAt":"2026-08-20T16:31:10.636Z"}` | `{"type":"hybrid","plans":[{"free":false,"name":"Usage-based","summary":"$0.015/page after 10,000 free pages","features":["OCR","Parsing","Partitioning","VLM enrichment","Chunking","Embedding"],"components":[{"per":{"qty":1,"unit":"page"},"kind":"metered","amount":0.015,"currency":"USD"}],"contactSales":false,"includedLimits":{"free_pages":"10,000"}}],"summary":"$0.015/page. 10,000 free pages.","currency":"USD","freeTier":true,"sourceUrl":"https://unstructured.io/insights/pricing-models-for-document-processing-at-scale","retrievedAt":"2026-10-02T16:20:07.914Z","startingPrice":{"unit":"page","amount":0.015,"currency":"USD"}}` |
| pricing.free_tier | yes | yes |
| pricing.model | open_source | freemium |
| pricing.price_level | free | low |
| pricing.starting_price | - | `{"amount":0.015,"currency":"USD"}` |
| pricing.transparent | yes | yes |
| release.cadence_days | 2 | - |
| release.history | `[{"url":"https://github.com/docling-project/docling/releases/tag/v2.138.0","date":"2026-10-12T06:14:54Z","type":"stable","version":"v2.138.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.137.0","date":"2026-10-09T14:12:20Z","type":"stable","version":"v2.137.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.136.0","date":"2026-10-09T12:08:31Z","type":"stable","version":"v2.136.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.135.0","date":"2026-10-07T10:42:24Z","type":"stable","version":"v2.135.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.134.0","date":"2026-10-06T04:56:24Z","type":"stable","version":"v2.134.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.133.0","date":"2026-10-03T11:27:20Z","type":"stable","version":"v2.133.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.132.0","date":"2026-10-01T09:44:36Z","type":"stable","version":"v2.132.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.131.0","date":"2026-09-29T07:58:11Z","type":"stable","version":"v2.131.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.130.0","date":"2026-09-22T15:33:48Z","type":"stable","version":"v2.130.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.129.0","date":"2026-09-18T09:18:32Z","type":"stable","version":"v2.129.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.128.0","date":"2026-09-16T15:12:42Z","type":"stable","version":"v2.128.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.127.0","date":"2026-09-14T08:57:03Z","type":"stable","version":"v2.127.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.126.0","date":"2026-09-04T15:47:33Z","type":"stable","version":"v2.126.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.125.0","date":"2026-09-03T14:28:00Z","type":"stable","version":"v2.125.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.124.0","date":"2026-08-31T13:36:37Z","type":"stable","version":"v2.124.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.123.1","date":"2026-08-28T15:12:34Z","type":"stable","version":"v2.123.1"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.123.0","date":"2026-08-26T16:15:07Z","type":"stable","version":"v2.123.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.122.0","date":"2026-08-25T09:28:52Z","type":"stable","version":"v2.122.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.121.0","date":"2026-08-20T09:05:04Z","type":"stable","version":"v2.121.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.120.3","date":"2026-08-18T07:50:48Z","type":"stable","version":"v2.120.3"}]` | - |
| security.certifications | - | `[{"name":"SOC 2 Type II","level":"Type II","status":"active"},{"name":"ISO 27001","status":"active"}]` |
| security.gdpr | - | yes |
| security.hipaa | - | yes |
| security.iso27001 | - | yes |
| security.soc2 | - | yes |
| security.vulnerabilities | `{"count":8,"source":"https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=docling-slim&per_page=100","last_12m":8,"max_severity":"HIGH"}` | - |

## Capabilities (Document AI)

| Capability | Docling | Unstructured |
|---|:--:|:--:|
| **Capabilities** |  |  |
| Prebuilt models | ✓ | ✓ |
| Custom model training | - | ✓ |
| Table extraction | ✓ | ✓ |
| Handwriting recognition | - | ✗ |
| Id document parsing | - | ✗ |
| Human in the loop review | - | ✗ |
| Confidence scoring | - | ✗ |
| LLM vlm based extraction | ✓ | ✓ |
| RPA ERP integration | - | ✗ |
| Open source | ✓ | ✓ |

*Source: vioscaleAI. Generated 2026-10-16T19:14:41.454Z. "-" = undocumented, not absent.*