DocuPipe · Schema

WorkflowV2RunRequest

Artificial IntelligenceDocument ExtractionDocument IntelligenceIntelligent Document ProcessingOCRDocument AI

Properties

Name Type Description
inputs array One entry per document. Every workflow input must receive at least one document; single-document inputs accept exactly one, stack inputs accept one or more (repeat the inputLabel). When the workflow h
timeout integer Timeout in seconds for this workflow run.
View JSON Schema on GitHub

JSON Schema

docupanda-workflow-v2-run-request-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/docupanda/json-schema/docupanda-workflow-v2-run-request-schema.json",
  "title": "WorkflowV2RunRequest",
  "x-generated": "2026-11-10",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/docupanda-workflow-api-openapi.yml#/components/schemas/WorkflowV2RunRequest",
  "properties": {
    "inputs": {
      "items": {
        "$ref": "#/$defs/WorkflowV2RunInput"
      },
      "type": "array",
      "title": "Inputs",
      "description": "One entry per document. Every workflow input must receive at least one document; single-document inputs accept exactly one, stack inputs accept one or more (repeat the inputLabel). When the workflow has a single input, inputLabel can be omitted and all entries are assigned to it."
    },
    "timeout": {
      "type": "integer",
      "title": "Timeout",
      "description": "Timeout in seconds for this workflow run."
    }
  },
  "type": "object",
  "required": [
    "inputs"
  ],
  "$defs": {
    "File": {
      "properties": {
        "contents": {
          "type": "string",
          "contentMediaType": "application/octet-stream",
          "title": "File Contents",
          "description": "Binary string representing the content of the file in base64 encoding."
        }
      },
      "type": "object",
      "required": [
        "contents"
      ],
      "title": "File"
    },
    "FileExtension": {
      "type": "string",
      "enum": [
        "pdf",
        "png",
        "jpeg",
        "webp",
        "tiff",
        "jp2",
        "txt",
        "json",
        "xml",
        "html",
        "doc",
        "docx",
        "csv",
        "xlsx",
        "xls",
        "eml"
      ],
      "title": "FileExtension"
    },
    "FileType": {
      "type": "string",
      "enum": [
        "pdf",
        "image",
        "text",
        "json",
        "html",
        "word",
        "table"
      ],
      "title": "FileType"
    },
    "InputDocument": {
      "properties": {
        "file": {
          "$ref": "#/$defs/File",
          "description": "File object containing the input document in base64 encoding."
        },
        "url": {
          "type": "string",
          "maxLength": 2083,
          "minLength": 1,
          "format": "uri",
          "title": "Document URL",
          "description": "URL pointing to the location of the input file."
        },
        "filename": {
          "type": "string",
          "title": "Filename",
          "description": "Name of the file, not including the file extension."
        },
        "fileExtension": {
          "$ref": "#/$defs/FileExtension",
          "title": "File Extension",
          "description": "Extension of the file."
        },
        "fileType": {
          "$ref": "#/$defs/FileType",
          "title": "File Type",
          "description": "Type of the file. If not provided, it will be determined from the file contents."
        }
      },
      "type": "object",
      "title": "Input Document"
    },
    "ProcessingMethod": {
      "type": "string",
      "enum": [
        "asImage",
        "removeWatermark"
      ],
      "title": "ProcessingMethod"
    },
    "WorkflowV2RunInput": {
      "properties": {
        "inputLabel": {
          "type": "string",
          "title": "Inputlabel",
          "description": "Label of the workflow input this document belongs to (case-sensitive). Required when the workflow has multiple inputs; optional when it has exactly one (single document or stack), where every entry is assigned to that input. Repeat the same label across entries to add several documents to a stack input."
        },
        "documentId": {
          "type": "string",
          "title": "Documentid",
          "description": "Reference an existing, fully processed workspace document. Provide exactly one of 'documentId' or 'document'."
        },
        "document": {
          "$ref": "#/$defs/InputDocument",
          "title": "Document",
          "description": "Or upload a new document inline using url or base64 file; it is parsed before the workflow runs."
        },
        "pages": {
          "items": {
            "type": "integer"
          },
          "type": "array",
          "title": "Pages",
          "description": "Zero-indexed pages. With an inline 'document': the pages to parse. With a 'documentId': the pages of that document the run's Standardize steps read, in place of their page range (other steps still see the whole document). Null/empty means all pages."
        },
        "dataset": {
          "type": "string",
          "title": "Dataset",
          "description": "Inline-upload only. Dataset to assign the uploaded document to."
        },
        "metadata": {
          "additionalProperties": true,
          "type": "object",
          "title": "Metadata",
          "description": "Inline-upload only. Optional metadata to associate with the document."
        },
        "parseVersion": {
          "type": "number",
          "title": "Parseversion",
          "description": "Inline-upload only. Parsing version."
        },
        "processingMethod": {
          "$ref": "#/$defs/ProcessingMethod",
          "title": "Processingmethod",
          "description": "Inline-upload only. Processing method."
        }
      },
      "type": "object",
      "title": "WorkflowV2RunInput"
    }
  }
}

Work with this as data

Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for schemas

4 MCP tools reach this
  • find_json_schemasBrowse and filter every JSON Schema in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/docupanda-workflow-v2-run-request"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.