Parsio Documents API

Upload, parse, list, and retrieve documents and their parsed data.

OpenAPI Specification

parsio-documents-api-openapi.yml Raw ↑
openapi: 3.0.1
info:
  title: Parsio Public Documents API
  description: Specification of the Parsio public REST API for AI-powered document and email parsing. Create and manage mailboxes (parsers), upload documents and emails for parsing, retrieve extracted structured JSON, manage parsing templates, and configure webhooks for real-time parsed-data delivery. All endpoints require an API key supplied via the X-API-Key request header.
  termsOfService: https://parsio.io/terms/
  contact:
    name: Parsio Support
    url: https://help.parsio.io
  version: '1.0'
servers:
- url: https://api.parsio.io
security:
- ApiKeyAuth: []
tags:
- name: Documents
  description: Upload, parse, list, and retrieve documents and their parsed data.
paths:
  /mailboxes/{mailbox_id}/doc-sync:
    parameters:
    - $ref: '#/components/parameters/MailboxId'
    post:
      operationId: parseDocumentSync
      tags:
      - Documents
      summary: Parse an HTML or text document synchronously.
      description: Submits an HTML or plain-text document and waits for the parsing result. Supply at least one of html or text; if both are present, html takes precedence.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ParseDocumentRequest'
      responses:
        '200':
          description: The parsed document.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Document'
        '401':
          $ref: '#/components/responses/Unauthorized'
  /mailboxes/{mailbox_id}/doc:
    parameters:
    - $ref: '#/components/parameters/MailboxId'
    post:
      operationId: parseDocumentAsync
      tags:
      - Documents
      summary: Parse an HTML or text document asynchronously.
      description: Submits an HTML or plain-text document for background parsing and returns immediately with a document ID. Results are delivered via webhooks or retrieved later by document ID.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ParseDocumentRequest'
      responses:
        '200':
          description: The accepted document.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Document'
        '401':
          $ref: '#/components/responses/Unauthorized'
  /mailboxes/{mailbox_id}/upload-sync:
    parameters:
    - $ref: '#/components/parameters/MailboxId'
    post:
      operationId: uploadFileSync
      tags:
      - Documents
      summary: Upload a file and wait for the parsing result.
      description: Uploads a single file (PDF, DOCX, image, HTML, JSON, XML, and more) up to 20MB and waits for the parsing result.
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/UploadFileRequest'
      responses:
        '200':
          description: The parsed document.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Document'
        '401':
          $ref: '#/components/responses/Unauthorized'
  /mailboxes/{mailbox_id}/upload:
    parameters:
    - $ref: '#/components/parameters/MailboxId'
    post:
      operationId: uploadFileAsync
      tags:
      - Documents
      summary: Upload a file for asynchronous parsing.
      description: Uploads a file (up to 50MB, ZIP archives supported) for background parsing and returns immediately. Results are delivered via webhooks or retrieved later by document ID.
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/UploadFileRequest'
      responses:
        '200':
          description: The accepted document.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Document'
        '401':
          $ref: '#/components/responses/Unauthorized'
  /mailboxes/{mailbox_id}/docs:
    parameters:
    - $ref: '#/components/parameters/MailboxId'
    get:
      operationId: listDocuments
      tags:
      - Documents
      summary: List documents.
      description: Lists documents in a mailbox with pagination and filters.
      parameters:
      - name: page
        in: query
        schema:
          type: integer
      - name: per_page
        in: query
        schema:
          type: integer
          maximum: 500
      - name: from
        in: query
        description: ISO 8601 start date filter.
        schema:
          type: string
          format: date
      - name: to
        in: query
        description: ISO 8601 end date filter.
        schema:
          type: string
          format: date
      - name: q
        in: query
        description: Free-text search query.
        schema:
          type: string
      - name: status
        in: query
        schema:
          $ref: '#/components/schemas/DocumentStatus'
      responses:
        '200':
          description: A paginated list of documents.
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/Document'
        '401':
          $ref: '#/components/responses/Unauthorized'
  /mailboxes/{mailbox_id}/docs/skip:
    parameters:
    - $ref: '#/components/parameters/MailboxId'
    post:
      operationId: skipDocuments
      tags:
      - Documents
      summary: Skip documents.
      description: Marks multiple documents as skipped.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/IdsRequest'
      responses:
        '200':
          description: Documents skipped.
        '401':
          $ref: '#/components/responses/Unauthorized'
  /docs/{document_id}:
    parameters:
    - $ref: '#/components/parameters/DocumentId'
    get:
      operationId: getDocument
      tags:
      - Documents
      summary: Get a parsed document.
      description: Retrieves a document and its extracted structured JSON by ID.
      responses:
        '200':
          description: The requested document.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Document'
        '401':
          $ref: '#/components/responses/Unauthorized'
  /docs/{document_id}/parse:
    parameters:
    - $ref: '#/components/parameters/DocumentId'
    post:
      operationId: reparseDocument
      tags:
      - Documents
      summary: Reparse a document.
      description: Reprocesses an existing document with the mailbox's current parser.
      responses:
        '200':
          description: The reparsed document.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Document'
        '401':
          $ref: '#/components/responses/Unauthorized'
  /mailboxes/{mailbox_id}/parsed:
    parameters:
    - $ref: '#/components/parameters/MailboxId'
    get:
      operationId: getParsedData
      tags:
      - Documents
      summary: Retrieve parsed data.
      description: Retrieves the parsed data for a mailbox's documents.
      parameters:
      - name: page
        in: query
        schema:
          type: integer
      - name: from
        in: query
        schema:
          type: string
          format: date
      - name: to
        in: query
        schema:
          type: string
          format: date
      responses:
        '200':
          description: Parsed data records.
          content:
            application/json:
              schema:
                type: array
                items:
                  type: object
                  additionalProperties: true
        '401':
          $ref: '#/components/responses/Unauthorized'
  /mailboxes/{mailbox_id}/emails:
    parameters:
    - $ref: '#/components/parameters/MailboxId'
    get:
      operationId: listCollectedEmails
      tags:
      - Documents
      summary: Get collected email addresses.
      description: Returns the email addresses collected by a mailbox.
      responses:
        '200':
          description: A list of collected email addresses.
          content:
            application/json:
              schema:
                type: array
                items:
                  type: string
                  format: email
        '401':
          $ref: '#/components/responses/Unauthorized'
components:
  parameters:
    MailboxId:
      name: mailbox_id
      in: path
      required: true
      description: The unique identifier of the mailbox (parser).
      schema:
        type: string
    DocumentId:
      name: document_id
      in: path
      required: true
      description: The unique identifier of the document.
      schema:
        type: string
  schemas:
    Document:
      type: object
      properties:
        doc_id:
          type: string
        parsing_in_progress:
          type: boolean
        status:
          $ref: '#/components/schemas/DocumentStatus'
        name:
          type: string
        content_type:
          type: string
        created_at:
          type: string
          format: date-time
        processed_at:
          type: string
          format: date-time
        json:
          type: object
          description: The extracted structured data.
          additionalProperties: true
    Error:
      type: object
      properties:
        error:
          type: string
        message:
          type: string
    ParseDocumentRequest:
      type: object
      properties:
        name:
          type: string
          description: Document identifier or subject line.
        html:
          type: string
          description: HTML markup to parse. Takes precedence over text when both are supplied.
        text:
          type: string
          description: Plain-text content to parse.
        from:
          type: string
          description: Sender address.
        to:
          type: string
          description: Recipient address.
        meta:
          type: object
          description: Custom metadata returned in the response as __meta__.
          additionalProperties: true
    IdsRequest:
      type: object
      required:
      - ids
      properties:
        ids:
          type: array
          items:
            type: string
    UploadFileRequest:
      type: object
      required:
      - file
      properties:
        file:
          type: string
          format: binary
          description: The file to upload and parse.
        meta:
          type: string
          description: Custom payload as a JSON object or JSON-encoded string.
    DocumentStatus:
      type: string
      enum:
      - new
      - parsing
      - parsed
      - fail
      - skipped
      - quota
      - exception
  responses:
    Unauthorized:
      description: API key missing or invalid.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: X-API-Key