OpenAI Moderations API

openapi: 3.1.0
info:
  title: OpenAI APIs OpenAI Moderations API
  description: >-
    API for detecting potentially harmful or unsafe content. Classifies text
    and images against categories such as hate, harassment, self-harm,
    sexual content, and violence.
  version: '1.0'
  contact:
    name: OpenAI Support
    email: [email protected]
    url: https://help.openai.com
  termsOfService: https://openai.com/policies/terms-of-use
externalDocs:
  description: OpenAI Moderations API Documentation
  url: https://platform.openai.com/docs/api-reference/moderations
servers:
  - url: https://api.openai.com/v1
    description: OpenAI Production API
tags:
  - name: Moderations
    description: Content moderation operations
security:
  - bearerAuth: []
paths:
  /moderations:
    post:
      operationId: createModeration
      summary: OpenAI APIs Create moderation
      description: >-
        Classifies if text and/or images are potentially harmful across
        several categories including hate, harassment, self-harm, sexual
        content, and violence.
      tags:
        - Moderations
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateModerationRequest'
      responses:
        '200':
          description: Moderation response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ModerationResponse'
        '400':
          description: Invalid request
        '401':
          description: Unauthorized - invalid or missing API key
        '429':
          description: Rate limit exceeded
        '500':
          description: Server error
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API Key
      description: OpenAI API key passed as a Bearer token
  schemas:
    CreateModerationRequest:
      type: object
      required:
        - input
      properties:
        input:
          oneOf:
            - type: string
            - type: array
              items:
                type: string
          description: The input text to classify for moderation
        model:
          type: string
          description: >-
            The content moderation model to use
            (text-moderation-latest, text-moderation-stable, omni-moderation-latest)
          default: omni-moderation-latest
          examples:
            - omni-moderation-latest
    ModerationResponse:
      type: object
      properties:
        id:
          type: string
          description: The unique identifier for the moderation request
        model:
          type: string
          description: The model used for moderation
        results:
          type: array
          items:
            $ref: '#/components/schemas/ModerationResult'
    ModerationResult:
      type: object
      properties:
        flagged:
          type: boolean
          description: Whether the content was flagged as potentially harmful
        categories:
          type: object
          properties:
            hate:
              type: boolean
              description: Content that expresses hate toward a group
            hate/threatening:
              type: boolean
              description: Hateful content that includes violence or threats
            harassment:
              type: boolean
              description: Content that harasses a target
            harassment/threatening:
              type: boolean
              description: Harassment content that includes violence or threats
            self-harm:
              type: boolean
              description: Content that promotes or depicts self-harm
            self-harm/intent:
              type: boolean
              description: Content where the speaker expresses intent to self-harm
            self-harm/instructions:
              type: boolean
              description: Content that provides instructions for self-harm
            sexual:
              type: boolean
              description: Sexual content
            sexual/minors:
              type: boolean
              description: Sexual content involving minors
            violence:
              type: boolean
              description: Content depicting violence
            violence/graphic:
              type: boolean
              description: Graphic violence content
        category_scores:
          type: object
          properties:
            hate:
              type: number
              description: Score for hate category
            hate/threatening:
              type: number
              description: Score for hate/threatening category
            harassment:
              type: number
              description: Score for harassment category
            harassment/threatening:
              type: number
              description: Score for harassment/threatening category
            self-harm:
              type: number
              description: Score for self-harm category
            self-harm/intent:
              type: number
              description: Score for self-harm/intent category
            self-harm/instructions:
              type: number
              description: Score for self-harm/instructions category
            sexual:
              type: number
              description: Score for sexual category
            sexual/minors:
              type: number
              description: Score for sexual/minors category
            violence:
              type: number
              description: Score for violence category
            violence/graphic:
              type: number
              description: Score for violence/graphic category