{
  "as_of": "2026-11-03T22:50:46.101Z",
  "url": "https://vendorindex.dev/category/doc-extraction/",
  "category": {
    "id": "doc-extraction",
    "name": "PDF & document extraction",
    "usage_metric": "pages"
  },
  "use_cases": [
    {
      "id": "bulk-text-extraction",
      "weights": [
        {
          "dimension": "cost",
          "weight": 0.35
        },
        {
          "dimension": "fit",
          "weight": 0.15
        },
        {
          "dimension": "integration",
          "weight": 0.1
        },
        {
          "dimension": "agent_friction",
          "weight": 0.15
        },
        {
          "dimension": "health",
          "weight": 0.15
        },
        {
          "dimension": "lock_in",
          "weight": 0.1
        }
      ],
      "ranking": [
        {
          "vendor": "docling",
          "total": 90,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 0
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 0
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "mineru",
          "total": 88.5,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 0
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 0
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "unstructured",
          "total": 88.5,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 0
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 0
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "marker",
          "total": 87.75,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 0
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 0
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "pymupdf",
          "total": 87,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 0
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 0
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "llamaparse",
          "total": 78.92,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 25
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 25
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "mistral-ocr",
          "total": 76.92,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 40
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 40
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "extend",
          "total": 75.33,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 50
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 50
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "pdfplumber",
          "total": 70.5,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 0
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 0
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "reducto",
          "total": 63.67,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 100
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 100
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "google-document-ai",
          "total": 56.17,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 100
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 100
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "azure-document-intelligence",
          "total": 53.17,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 100
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 100
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "aws-textract",
          "total": 29.5,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 150
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 150
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        }
      ]
    },
    {
      "id": "complex-doc-parsing",
      "weights": [
        {
          "dimension": "fit",
          "weight": 0.4
        },
        {
          "dimension": "cost",
          "weight": 0.12
        },
        {
          "dimension": "integration",
          "weight": 0.1
        },
        {
          "dimension": "agent_friction",
          "weight": 0.13
        },
        {
          "dimension": "health",
          "weight": 0.15
        },
        {
          "dimension": "lock_in",
          "weight": 0.1
        }
      ],
      "ranking": [
        {
          "vendor": "docling",
          "total": 90,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 0
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 0
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "mineru",
          "total": 88.7,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 0
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 0
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "unstructured",
          "total": 88.7,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 0
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 0
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "marker",
          "total": 87.95,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 0
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 0
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "mistral-ocr",
          "total": 83.45,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 40
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 40
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "extend",
          "total": 83.4,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 50
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 50
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "llamaparse",
          "total": 83.15,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 25
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 25
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "reducto",
          "total": 79.4,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 100
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 100
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "google-document-ai",
          "total": 72.7,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 100
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 100
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "azure-document-intelligence",
          "total": 69.7,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 100
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 100
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "aws-textract",
          "total": 68.7,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 150
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 150
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "pymupdf",
          "total": 60.73,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 0
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 0
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        },
        {
          "vendor": "pdfplumber",
          "total": 59.43,
          "insufficient_data": false,
          "costs": [
            {
              "volume": 10000,
              "monthly": 0
            }
          ],
          "profile_costs": [
            {
              "id": "parse-10k",
              "name": "Layout parse (10k pages/mo)",
              "monthly": 0
            }
          ],
          "free_tier": true,
          "last_verified": "2026-11-03",
          "staleness": "fresh",
          "divergence": "none"
        }
      ]
    }
  ]
}