{
  "openapi": "3.0.1",
  "info": {
    "title": "ConvertAPI",
    "description": "# High-Performance File Conversion API\nConvert Word, Excel, PowerPoint, HTML, PDF and Image formats with our powerful file conversion service.\nWe support more than [200 file types.]( https://www.convertapi.com/doc/file-formats)",
    "termsOfService": "https://www.convertapi.com/terms",
    "contact": {
      "url": "https://www.convertapi.com/support",
      "email": "support@convertapi.com"
    },
    "license": {
      "name": "Apache 2.0",
      "url": "http://www.apache.org/licenses/LICENSE-2.0.html"
    },
    "version": "v2"
  },
  "servers": [
    {
      "url": "https://v2.convertapi.com"
    },
    {
      "url": "https://eu-v2.convertapi.com"
    },
    {
      "url": "https://uk-v2.convertapi.com"
    },
    {
      "url": "https://us-v2.convertapi.com"
    },
    {
      "url": "https://ca-v2.convertapi.com"
    },
    {
      "url": "https://as-v2.convertapi.com"
    },
    {
      "url": "https://au-v2.convertapi.com"
    }
  ],
  "paths": {
    "/convert/pdf/to/extract": {
      "summary": "Extract PDF API",
      "description": "AI-powered extraction of structured data from invoices, receipts, and forms with custom fields and confidence levels.",
      "post": {
        "tags": [
          "Conversion"
        ],
        "externalDocs": {
          "description": "Read more about the converter",
          "url": "https://www.convertapi.com/pdf-to-extract"
        },
        "requestBody": {
          "content": {
            "multipart/form-data": {
              "schema": {
                "required": [
                  "File"
                ],
                "type": "object",
                "properties": {
                  "Timeout": {
                    "maximum": 1200,
                    "minimum": 10,
                    "type": "integer",
                    "description": "Conversion timeout in seconds.",
                    "default": 900,
                    "x-ca-featured": false,
                    "x-ca-label": "Timeout",
                    "x-ca-group": "Execution",
                    "x-ca-type": "Integer",
                    "x-ca-representation": "Default",
                    "x-ca-range": {
                      "from": "10",
                      "to": "1200"
                    }
                  },
                  "StoreFile": {
                    "type": "boolean",
                    "description": "When the `StoreFile` parameter is set to `True`, your converted file is written to ConvertAPI’s encrypted, temporary storage and made available via a time-limited secure download URL, valid for up to 3 hours. After this period, the file is permanently deleted.\r\n\r\nWhen `StoreFile` is set to `False`, conversion happens entirely in-memory. The raw file bytes are streamed back in the API response without touching disk or external storage, ensuring maximum security and zero persistence so that only you can access the content.\r\n",
                    "default": false,
                    "x-ca-featured": false,
                    "x-ca-label": "Store file",
                    "x-ca-group": "Output",
                    "x-ca-type": "Bool",
                    "x-ca-representation": "Default"
                  },
                  "File": {
                    "type": "string",
                    "description": "File to be converted. Value can be URL or file content.",
                    "format": "binary",
                    "x-ca-featured": true,
                    "x-ca-label": "File",
                    "x-ca-group": "Input",
                    "x-ca-type": "File",
                    "x-ca-representation": "Default",
                    "x-ca-allowed-extensions": [
                      "pdf"
                    ]
                  },
                  "FileName": {
                    "type": "string",
                    "description": "The `FileName` property defines the name of the output file(s) generated by the file conversion API, ensuring safe and\r\nunique file naming. It sanitizes input filenames to remove potentially harmful characters, automatically appends the\r\ncorrect file extension based on the target format, and includes an indexing feature to distinguish multiple output files\r\nfrom a single input. For example, converting `report.docx` to PDF format might result in `report.pdf` for a single file,\r\nor `report_0.pdf`, `report_1.pdf` for multiple files, ensuring each output file is uniquely identifiable.",
                    "x-ca-featured": false,
                    "x-ca-label": "Output file name",
                    "x-ca-group": "Output",
                    "x-ca-type": "String",
                    "x-ca-representation": "Default",
                    "x-ca-range": {
                      "from": "1",
                      "to": "200"
                    }
                  },
                  "Password": {
                    "type": "string",
                    "description": "Sets the password to open protected PDF.",
                    "x-ca-featured": false,
                    "x-ca-label": "Open password",
                    "x-ca-group": "Input",
                    "x-ca-type": "String",
                    "x-ca-representation": "Default"
                  },
                  "DocumentType": {
                    "enum": [
                      "auto",
                      "invoice",
                      "receipt",
                      "contract",
                      "identification",
                      "financial",
                      "form",
                      "manual"
                    ],
                    "type": "string",
                    "description": "The `DocumentType` parameter specifies the type of document you're processing, enabling the AI to precisely extract structured data based on the selected document category. Selecting the correct document type improves extraction accuracy by applying optimized data extraction rules tailored for each category. Choose manual if you prefer to exclusively define `CustomExtractionData` parameter.\r\n\r\nSelect the DocumentType that matches your document:\r\n\r\n- **Auto** - Attempts to identify the document as one of the listed types and applies the corresponding extraction rules.\r\n\r\n- **Invoice** - Extract structured data from invoices, including invoice number, dates, totals, vendor details, and line items.\r\n\r\n- **Receipt** - Optimized extraction for payment receipts, capturing dates, totals, vendor details, and payment methods.\r\n\r\n- **Contract** - Captures critical details from contracts or agreements, including parties involved, dates, terms, and conditions.\r\n\r\n- **Identification** - Designed for identification documents like passports, driver's licenses, or national ID cards, extracting names, dates, document numbers, and other identifying information.\r\n\r\n- **Financial** - Specifically targets financial documents, including bank statements and transaction records, extracting transaction dates, amounts, balances, and descriptions.\r\n\r\n- **Form** - Extracts structured data from standard forms containing predefined fields, ideal for surveys, applications, and questionnaires.\r\n\r\n- **Manual** - Disables predefined AI document extraction presets. Only manually configured extraction parameters are used, giving full control to the user.",
                    "default": "auto",
                    "x-ca-featured": true,
                    "x-ca-label": "Document Type",
                    "x-ca-group": "AI Detection Options",
                    "x-ca-type": "Collection",
                    "x-ca-representation": "Dropdown",
                    "x-ca-values": {
                      "auto": "Automatically Detect Document Type",
                      "invoice": "Invoice",
                      "receipt": "Receipt or Payment Slip",
                      "contract": "Contract / Agreement",
                      "identification": "Identification Document (ID, passport, etc.)",
                      "financial": "Bank Statement / Transaction Records",
                      "form": "Form with Structured Fields",
                      "manual": "Custom Extraction Only"
                    }
                  },
                  "CustomExtractionData": {
                    "type": "string",
                    "description": "A JSON array defining specific values to extract.\r\n\r\n#### Example JSON\r\n\r\n```json\r\n[\r\n  {\r\n    \"FieldName\": \"TotalResult\",\r\n    \"Extract\": \"total price\"\r\n  },\r\n  {\r\n    \"FieldName\": \"ServiceName\",\r\n    \"Extract\": \"most expensive service name\"\r\n  }\r\n]\r\n```",
                    "x-ca-featured": false,
                    "x-ca-label": "Custom Extraction Data",
                    "x-ca-group": "AI Detection Options",
                    "x-ca-type": "String",
                    "x-ca-representation": "Default"
                  },
                  "MinimumConfidence": {
                    "maximum": 0.99,
                    "minimum": 0.01,
                    "type": "number",
                    "description": "Sets the minimum confidence threshold for AI-based detection of sensitive data. Higher values reduce false positives but may miss subtle matches.",
                    "default": 0.5,
                    "x-ca-featured": false,
                    "x-ca-label": "Minimum confidence",
                    "x-ca-group": "AI Detection Options",
                    "x-ca-type": "Double",
                    "x-ca-representation": "Default",
                    "x-ca-range": {
                      "from": "0.01",
                      "to": "0.99"
                    }
                  }
                }
              }
            }
          }
        },
        "responses": {
          "200": {
            "description": "Success",
            "content": {
              "application/json": {
                "schema": {
                  "type": "object",
                  "properties": {
                    "ConversionCost": {
                      "type": "integer",
                      "description": "This amount will be deducted from your balance after the conversion.",
                      "format": "int32",
                      "example": 1
                    },
                    "Files": {
                      "type": "array",
                      "items": {
                        "type": "object",
                        "properties": {
                          "FileName": {
                            "type": "string",
                            "description": "Name of the converted file.",
                            "example": "myfile.pdf"
                          },
                          "FileExt": {
                            "type": "string",
                            "description": "File type (file name extension)",
                            "example": "pdf"
                          },
                          "FileSize": {
                            "type": "integer",
                            "description": "File size",
                            "format": "int32",
                            "example": 111955
                          },
                          "FileId": {
                            "type": "string",
                            "description": "File ID",
                            "example": "25811safe8e61dd3f51ef00ee5f58b92"
                          },
                          "Url": {
                            "type": "string",
                            "description": "File URL",
                            "example": "https://v2.convertapi.com/d/v01plsb72o0cmdooq90w4d1lnqsf6oy4/myfile.pdf"
                          },
                          "FileData": {
                            "type": "string",
                            "description": "Base64 encoded file data",
                            "format": "base64",
                            "example": "JVBERi0xLjcKJb662+4KMSAwIG9iago8PC9UeXBlIC9DYXRhbG9n..."
                          }
                        }
                      }
                    }
                  },
                  "externalDocs": {
                    "url": "https://www.convertapi.com/doc/content-types#applicationjson-1"
                  }
                }
              },
              "multipart/mixed": {
                "schema": {
                  "type": "string",
                  "format": "binary",
                  "externalDocs": {
                    "url": "https://www.convertapi.com/doc/content-types#multipartmixed"
                  }
                },
                "example": "--43cf1475-ab15-4c6b-b5ee-e2cbcedfe92f\nConversionCost: 1\nContent-Type: application/octet-stream\nContent-Disposition: attachment; filename=\"my_file.pdf\"; size=8475\n\n--FILE CONTENT--\n--43cf1475-ab15-4c6b-b5ee-e2cbcedfe92f--\n"
              },
              "application/octet-stream": {
                "schema": {
                  "type": "string",
                  "format": "binary",
                  "externalDocs": {
                    "url": "https://www.convertapi.com/doc/content-types#applicationoctet-stream-1"
                  }
                }
              }
            }
          },
          "400": {
            "$ref": "#/components/responses/400"
          },
          "401": {
            "$ref": "#/components/responses/401"
          },
          "415": {
            "$ref": "#/components/responses/415"
          },
          "500": {
            "$ref": "#/components/responses/500"
          },
          "503": {
            "$ref": "#/components/responses/503"
          }
        },
        "security": [
          {
            "secret": [ ]
          },
          {
            "token": [ ]
          },
          {
            "jwt": [ ]
          }
        ]
      },
      "x-ca-overview": "Automatically extract key information from invoices, receipts, forms, and other documents. Whether you're automating business workflows, simplifying data entry, or streamlining document processing, our AI-powered text extraction tool offers accurate, fast, and user-friendly data extraction solutions. Start transforming your documents into structured data today with our reliable Data Extraction API.",
      "x-ca-meta-title": "Extract Data from Documents with AI - Data Extraction API",
      "x-ca-meta-description": "Easily extract structured data from invoices, receipts, and forms using AI or JSON. Automate document processing with our smart PDF Data Extraction API.",
      "x-ca-source-formats": "pdf",
      "x-ca-destination-formats": "json",
      "x-ca-tags": [
        "ai",
        "extract",
        "pdf"
      ]
    }
  },
  "components": {
    "schemas": {
      "fileId": {
        "maxLength": 32,
        "minLength": 32,
        "type": "string",
        "description": "Uploaded File ID",
        "example": "25811safe8e61dd3f51ef00ee5f58b92"
      },
      "error": {
        "type": "object",
        "properties": {
          "Code": {
            "type": "integer",
            "description": "Error message code",
            "format": "int32",
            "example": 4000
          },
          "Message": {
            "type": "string",
            "description": "Error message text",
            "example": "Parameter validation error."
          }
        },
        "externalDocs": {
          "url": "https://www.convertapi.com/doc/response-codes"
        }
      }
    },
    "responses": {
      "400": {
        "description": "Malformed request",
        "content": {
          "application/json": {
            "schema": {
              "$ref": "#/components/schemas/error"
            }
          }
        }
      },
      "401": {
        "description": "Authentication error",
        "content": {
          "application/json": {
            "schema": {
              "$ref": "#/components/schemas/error"
            }
          }
        }
      },
      "415": {
        "description": "File type error",
        "content": {
          "application/json": {
            "schema": {
              "$ref": "#/components/schemas/error"
            }
          }
        }
      },
      "500": {
        "description": "Conversion failure",
        "content": {
          "application/json": {
            "schema": {
              "$ref": "#/components/schemas/error"
            }
          }
        }
      },
      "503": {
        "description": "Conversion rate limit error",
        "content": {
          "application/json": {
            "schema": {
              "$ref": "#/components/schemas/error"
            }
          }
        }
      }
    },
    "parameters": {
      "fileId": {
        "name": "fileId",
        "in": "path",
        "description": "File ID",
        "required": true,
        "schema": {
          "$ref": "#/components/schemas/fileId"
        }
      },
      "src": {
        "name": "src",
        "in": "path",
        "description": "Source file format (docx, pdf, jpg etc.)",
        "required": true,
        "schema": {
          "type": "string"
        }
      },
      "dst": {
        "name": "dst",
        "in": "path",
        "description": "Destination file format (docx, pdf, jpg etc.)",
        "required": true,
        "schema": {
          "type": "string"
        }
      }
    },
    "headers": {
      "content-disposition": {
        "description": "File information ([docummentation](https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Disposition))",
        "schema": {
          "type": "string"
        }
      },
      "file-name": {
        "description": "File name",
        "schema": {
          "type": "string"
        }
      },
      "file-ext": {
        "description": "File name extension",
        "schema": {
          "type": "string"
        }
      },
      "file-size": {
        "description": "File size",
        "schema": {
          "type": "integer"
        }
      }
    },
    "securitySchemes": {
      "secret": {
        "type": "http",
        "description": "[Get `Secret`](https://www.convertapi.com/a/secret)",
        "scheme": "bearer"
      },
      "token": {
        "type": "http",
        "description": "[Get `Token`](https://www.convertapi.com/a/api-tokens)",
        "scheme": "bearer"
      },
      "jwt": {
        "type": "http",
        "description": "[Get `JWT`](https://www.convertapi.com/a/jwt-tokens)",
        "scheme": "bearer",
        "bearerFormat": "JWT"
      }
    }
  },
  "tags": [
    {
      "name": "Conversion",
      "description": "File Conversion API call",
      "externalDocs": {
        "description": "File Conversion related operations",
        "url": "https://www.convertapi.com/doc/content-types"
      }
    },
    {
      "name": "File Server",
      "description": "ConvertAPI temporary file storage",
      "externalDocs": {
        "description": "File Server related operations",
        "url": "https://www.convertapi.com/doc/upload"
      }
    },
    {
      "name": "User",
      "description": "API User",
      "externalDocs": {
        "description": "API User related operations",
        "url": "https://www.convertapi.com/doc/user"
      }
    }
  ],
  "externalDocs": {
    "description": "Find out more about ConvertAPI",
    "url": "https://www.convertapi.com/doc"
  }
}