{
  "x402Version": 2,
  "id": 38020,
  "slug": "38020",
  "resource": "https://pdf.openverbs.com/v1/extract",
  "description": "Extract plain text and metadata (title, author, producer, page count) from a PDF supplied by URL or base64 — heavy pdf.js parsing an agent can't self-run.",
  "type": "http",
  "serviceName": "PDF Text Extraction",
  "resourceType": "Blockchain Data",
  "accepts": [
    {
      "scheme": "exact",
      "network": "eip155:8453",
      "payTo": "0xb3f4de103F34b99f0Da19B4F16D6B53a14C2194A",
      "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
      "amount": "6000",
      "amountUsd": 0.006,
      "maxTimeoutSeconds": 300
    }
  ],
  "outputSchema": {
    "properties": {
      "example": {
        "type": "object"
      },
      "type": {
        "type": "string"
      }
    },
    "required": [
      "type"
    ],
    "type": "object"
  },
  "extensions": {
    "bazaar": {
      "info": {
        "input": {
          "body": {
            "url": "https://example.com/doc.pdf"
          },
          "bodyType": "json",
          "method": "POST",
          "type": "http"
        },
        "output": {
          "example": {
            "characters": 18432,
            "extractedPages": 12,
            "info": {
              "author": "Example Corp",
              "creationDate": "D:20250131120000Z",
              "creator": "LaTeX",
              "encrypted": false,
              "keywords": null,
              "modificationDate": null,
              "pdfVersion": "1.7",
              "producer": "pdfTeX-1.40.25",
              "subject": null,
              "title": "Annual Report 2025"
            },
            "pages": 12,
            "source": "url",
            "text": "Annual Report 2025\nExecutive summary…",
            "truncated": false,
            "url": "https://example.com/report.pdf"
          },
          "type": "json"
        }
      },
      "schema": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {
          "input": {
            "additionalProperties": false,
            "properties": {
              "body": {
                "additionalProperties": false,
                "properties": {
                  "maxPages": {
                    "description": "Cap the number of pages extracted (from the start). Default 500.",
                    "maximum": 500,
                    "minimum": 1,
                    "type": "integer"
                  },
                  "pdf": {
                    "description": "Base64-encoded PDF bytes (≤5 MB decoded). Provide this or `url`.",
                    "maxLength": 7000000,
                    "type": "string"
                  },
                  "perPage": {
                    "description": "When true, also return the text split per page as `perPage[]`.",
                    "type": "boolean"
                  },
                  "url": {
                    "description": "Public http(s) URL of the PDF to fetch. Private/loopback/link-local addresses are rejected. Provide this or `pdf`.",
                    "format": "uri",
                    "maxLength": 2048,
                    "type": "string"
                  }
                },
                "type": "object"
              },
              "bodyType": {
                "enum": [
                  "json",
                  "form-data",
                  "text"
                ],
                "type": "string"
              },
              "method": {
                "enum": [
                  "POST"
                ],
                "type": "string"
              },
              "type": {
                "const": "http",
                "type": "string"
              }
            },
            "required": [
              "type",
              "method",
              "bodyType",
              "body"
            ],
            "type": "object"
          },
          "output": {
            "properties": {
              "example": {
                "type": "object"
              },
              "type": {
                "type": "string"
              }
            },
            "required": [
              "type"
            ],
            "type": "object"
          }
        },
        "required": [
          "input"
        ],
        "type": "object"
      }
    }
  },
  "tags": [
    "pdf",
    "pdf-extract",
    "pdf-to-text",
    "extract-text",
    "document-text",
    "bazaar"
  ],
  "sourceHost": "pdf.openverbs.com",
  "lastUpdated": "2026-10-06T17:03:24.637Z",
  "quality": {
    "calls30d": 2,
    "uniquePayers30d": 1,
    "lastCalledAt": "2026-10-06T17:03:24.364Z"
  },
  "metadata": {
    "serviceName": "PDF Text Extraction",
    "extensions": {
      "bazaar": {
        "info": {
          "input": {
            "body": {
              "url": "https://example.com/doc.pdf"
            },
            "bodyType": "json",
            "method": "POST",
            "type": "http"
          },
          "output": {
            "example": {
              "characters": 18432,
              "extractedPages": 12,
              "info": {
                "author": "Example Corp",
                "creationDate": "D:20250131120000Z",
                "creator": "LaTeX",
                "encrypted": false,
                "keywords": null,
                "modificationDate": null,
                "pdfVersion": "1.7",
                "producer": "pdfTeX-1.40.25",
                "subject": null,
                "title": "Annual Report 2025"
              },
              "pages": 12,
              "source": "url",
              "text": "Annual Report 2025\nExecutive summary…",
              "truncated": false,
              "url": "https://example.com/report.pdf"
            },
            "type": "json"
          }
        },
        "schema": {
          "$schema": "https://json-schema.org/draft/2020-12/schema",
          "properties": {
            "input": {
              "additionalProperties": false,
              "properties": {
                "body": {
                  "additionalProperties": false,
                  "properties": {
                    "maxPages": {
                      "description": "Cap the number of pages extracted (from the start). Default 500.",
                      "maximum": 500,
                      "minimum": 1,
                      "type": "integer"
                    },
                    "pdf": {
                      "description": "Base64-encoded PDF bytes (≤5 MB decoded). Provide this or `url`.",
                      "maxLength": 7000000,
                      "type": "string"
                    },
                    "perPage": {
                      "description": "When true, also return the text split per page as `perPage[]`.",
                      "type": "boolean"
                    },
                    "url": {
                      "description": "Public http(s) URL of the PDF to fetch. Private/loopback/link-local addresses are rejected. Provide this or `pdf`.",
                      "format": "uri",
                      "maxLength": 2048,
                      "type": "string"
                    }
                  },
                  "type": "object"
                },
                "bodyType": {
                  "enum": [
                    "json",
                    "form-data",
                    "text"
                  ],
                  "type": "string"
                },
                "method": {
                  "enum": [
                    "POST"
                  ],
                  "type": "string"
                },
                "type": {
                  "const": "http",
                  "type": "string"
                }
              },
              "required": [
                "type",
                "method",
                "bodyType",
                "body"
              ],
              "type": "object"
            },
            "output": {
              "properties": {
                "example": {
                  "type": "object"
                },
                "type": {
                  "type": "string"
                }
              },
              "required": [
                "type"
              ],
              "type": "object"
            }
          },
          "required": [
            "input"
          ],
          "type": "object"
        }
      }
    }
  },
  "liveness": {
    "reliability": null
  },
  "verified": false,
  "featured": false,
  "provider": {
    "host": "pdf.openverbs.com",
    "manifest_name": "pdf.openverbs.com",
    "source": "cdp-mirror",
    "source_manifest_url": "https://api.cdp.coinbase.com/platform/v2/x402/discovery/resources",
    "submitted_at": "2026-10-14T01:15:01.050Z"
  },
  "exampleResponse": {
    "example": {},
    "type": "string"
  }
}