openapi: 3.0.3
info:
  title: Reducto Cancel Classify API
  description: REST API for parsing, extracting, splitting, classifying, and editing complex documents. Supports PDFs, Word files, spreadsheets, presentations, and scanned images using layout-aware OCR and vision language models.
  version: v1.11.80-78-gc5c4ff11c
  contact:
    url: https://reducto.ai/
    email: support@reducto.ai
  license:
    name: Proprietary
servers:
- url: https://platform.reducto.ai
security:
- BearerAuth: []
tags:
- name: Classify
paths:
  /classify:
    post:
      summary: Classify
      operationId: classify_classify_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ClassifyConfig'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ClassifyResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      tags:
      - Classify
components:
  schemas:
    CriteriaConfidence:
      properties:
        criterion:
          type: string
          title: Criterion
        confidence:
          type: string
          enum:
          - high
          - low
          title: Confidence
      type: object
      required:
      - criterion
      - confidence
      title: CriteriaConfidence
      description: Confidence result for a single criterion.
    UploadResponse:
      properties:
        file_id:
          type: string
          title: File Id
        presigned_url:
          type: string
          nullable: true
          title: Presigned Url
      type: object
      required:
      - file_id
      title: UploadResponse
    ClassifyResponseCategory:
      properties:
        category:
          type: string
          title: Category
      type: object
      required:
      - category
      title: ClassifyResponseCategory
    ResponseConfidence:
      properties:
        categories:
          items:
            $ref: '#/components/schemas/CategoryConfidence'
          type: array
          title: Categories
      type: object
      required:
      - categories
      title: ResponseConfidence
      description: Overall confidence breakdown for classification response.
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
        input:
          title: Input
        ctx:
          type: object
          title: Context
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
    ClassifyResponse:
      properties:
        response_type:
          type: string
          title: Response Type
          default: classify
          enum:
          - classify
        job_id:
          type: string
          title: Job Id
        result:
          $ref: '#/components/schemas/ClassifyResponseCategory'
        response_confidence:
          $ref: '#/components/schemas/ResponseConfidence'
          nullable: true
        usage:
          $ref: '#/components/schemas/ClassifyUsage'
          nullable: true
        duration:
          type: number
          nullable: true
          title: Duration
          description: The duration of the classify request in seconds.
      type: object
      required:
      - job_id
      - result
      title: ClassifyResponse
      description: Response from classify job - returned when polling /job/{job_id}
    ClassifyConfig:
      properties:
        persist_results:
          type: boolean
          title: Persist Results
          description: If True, persist the results indefinitely. Defaults to False.
          default: false
        input:
          anyOf:
          - type: string
          - items:
              type: string
            type: array
          - $ref: '#/components/schemas/UploadResponse'
          title: Input
          description: "For parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following:\n            1. A publicly available URL\n            2. A presigned S3 URL\n            3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document\n            4. A jobid:// prefixed URL obtained from a previous /parse invocation\n            5. A list of URLs (for multi-document pipelines, V3 API only)\n\n            For edit pipelines, this should be a string containing the edit instructions "
        classification_schema:
          items:
            $ref: '#/components/schemas/ClassificationCategory'
          type: array
          title: Classification Schema
          description: A list of classification categories and their matching criteria.
          default: []
        page_range:
          anyOf:
          - $ref: '#/components/schemas/PageRange'
          - items:
              $ref: '#/components/schemas/PageRange'
            type: array
          - items:
              type: integer
            type: array
          title: Page Range
          description: The page range to process (1-indexed). By default, the first 5 pages are used. If more than 25 pages are selected, only the first 25 (after sorting) are used. Only applies to PDFs; ignored for other document types.
          nullable: true
        document_metadata:
          type: string
          nullable: true
          title: Document Metadata
          description: Optional document-level metadata to include in classification prompts.
      type: object
      required:
      - input
      title: ClassifyConfig
    ClassificationCategory:
      properties:
        category:
          type: string
          title: Category
          description: The category name/label that documents will be classified into (e.g., 'invoice', 'contract', 'receipt').
        criteria:
          items:
            type: string
          type: array
          title: Criteria
          description: A list of criteria, keywords, or descriptions that define what characteristics a document must have to be classified into this category (e.g., ['contains billing information', 'has itemized charges']).
      type: object
      required:
      - category
      - criteria
      title: ClassificationCategory
      description: A single classification category with its matching criteria.
    PageRange:
      properties:
        start:
          type: integer
          nullable: true
          title: Start
          description: The page number to start processing from (1-indexed).
        end:
          type: integer
          nullable: true
          title: End
          description: The page number to stop processing at (1-indexed).
      type: object
      title: PageRange
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ClassifyUsage:
      properties:
        num_pages:
          type: integer
          title: Num Pages
        num_categories:
          type: integer
          title: Num Categories
        credits:
          type: number
          nullable: true
          title: Credits
      type: object
      required:
      - num_pages
      - num_categories
      title: ClassifyUsage
    CategoryConfidence:
      properties:
        category:
          type: string
          title: Category
        confidence:
          type: number
          title: Confidence
        criteria_confidence:
          items:
            $ref: '#/components/schemas/CriteriaConfidence'
          type: array
          title: Criteria Confidence
      type: object
      required:
      - category
      - confidence
      - criteria_confidence
      title: CategoryConfidence
      description: Confidence result for a category.
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      description: API key passed as a Bearer token in the Authorization header.