openapi: 3.1.0
info:
  title: extract API
  version: 1.0.0
servers:
- url: https://studio.runautomat.com
  description: Production
tags:
- name: extract
paths:
  /api/extract:
    post:
      operationId: extract
      summary: Extract Document
      description: 'Extract structured data from a document using a configured extractor.


        Upload a document (PDF, image, or other supported format) along with an extractor ID,

        and receive the extracted data matching your extractor''s schema.


        **File Input Options:**

        - **Binary upload**: Directly upload the file (max 4.5 MB)

        - **Base64**: Pass base64-encoded file content (max 4.5 MB)

        - **Data URL**: Pass a data URL (max 4.5 MB)

        - **URL**: Pass a publicly accessible URL to the document (up to 35 MB)


        **File Size Limits:**

        Binary, Base64, and Data URL inputs are limited to **4.5 MB** on the Pay As You Go plan.

        For larger files up to **35 MB**, use the URL option.

        Need higher limits? Contact sales at https://runautomat.com/contact'
      tags:
      - extract
      parameters:
      - name: Authorization
        in: header
        description: Bearer authentication
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Response with status 200
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/type_extract:ExtractResponse'
        '400':
          description: 'The request is malformed or missing required fields.

            Check that you''ve provided all required fields: `file` and `extractorId`.'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/type_extract:ErrorResponse'
        '401':
          description: 'The API key is missing, invalid, or has been revoked.

            Ensure you''re using a valid API key in the `Authorization: Bearer <api_key>` header.'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/type_extract:ErrorResponse'
        '422':
          description: 'The extraction could not be completed. This may occur if:

            - The extractor ID doesn''t exist or you don''t have access to it

            - The document format is not supported

            - The document could not be processed'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/type_extract:ErrorResponse'
        '500':
          description: An unexpected error occurred. Please try again or contact support.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/type_extract:ErrorResponse'
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                extractorId:
                  type: string
                  description: 'The unique identifier of the extractor to use for extraction.

                    You can find this in the Automat dashboard or when creating an extractor via the API.'
                file:
                  type: string
                  format: binary
                  description: 'The document to extract data from. Can be:

                    - A binary file upload

                    - A URL string (http:// or https://)

                    - A base64-encoded string

                    - A data URL string'
                mimeType:
                  type: string
                  description: 'The MIME type of the file. Required when `file` is a string (URL, base64, or data URL).

                    Examples: `application/pdf`, `image/png`, `image/jpeg`'
                filename:
                  type: string
                  description: "Optional filename for the document. If not provided, will be inferred from \nthe File object name or URL path."
                extractorVersionId:
                  type: string
                  description: Pin extraction to a specific extractor version
                config:
                  type: object
                  additionalProperties:
                    description: Any type
                  description: Override model configuration for this request
                timeout:
                  type: integer
                  description: Timeout in seconds (1-300)
              required:
              - extractorId
              - file
components:
  schemas:
    type_extract:ErrorResponse:
      type: object
      properties:
        error:
          type: string
          description: Machine-readable error code (e.g., "bad_request", "unauthorized")
        message:
          type: string
          description: Human-readable error message describing what went wrong
      required:
      - error
      - message
      description: Standard error response format
      title: ErrorResponse
    type_extract:ExtractResponse:
      type: object
      properties:
        data:
          type: object
          additionalProperties:
            description: Any type
          description: 'The extracted data matching your extractor''s schema.

            The structure depends on how you configured your extractor.'
      required:
      - data
      description: Response from a successful extraction request
      title: ExtractResponse
  securitySchemes:
    BearerAuthScheme:
      type: http
      scheme: bearer