Mistral Moderation API

openapi: 3.1.0
info:
  title: Mistral AI Mistral Moderation API
  description: >-
    Content moderation and classification API for detecting potentially harmful
    or inappropriate content. Supports text and chat moderation across safety
    categories including violence, sexual content, hate speech, self-harm,
    dangerous content, and more.
  version: '1.0'
  contact:
    name: Mistral AI Support
    url: https://docs.mistral.ai/
    email: [email protected]
  termsOfService: https://mistral.ai/terms/
externalDocs:
  description: Mistral Moderation API Documentation
  url: https://docs.mistral.ai/api/#moderation
servers:
  - url: https://api.mistral.ai/v1
    description: Mistral AI Production
tags:
  - name: Moderation
    description: Content moderation and classification operations
security:
  - bearerAuth: []
paths:
  /moderations:
    post:
      operationId: createModeration
      summary: Mistral AI Moderate text content
      description: >-
        Classify text content for potential policy violations across safety
        categories. Returns category-level flags and scores.
      tags:
        - Moderation
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ModerationRequest'
      responses:
        '200':
          description: Moderation result
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ModerationResponse'
        '400':
          description: Bad request
        '401':
          description: Unauthorized
        '429':
          description: Rate limit exceeded
  /chat/moderations:
    post:
      operationId: createChatModeration
      summary: Mistral AI Moderate chat conversation
      description: >-
        Classify a chat conversation for potential policy violations. Evaluates
        multi-turn conversations including system, user, and assistant messages.
      tags:
        - Moderation
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ChatModerationRequest'
      responses:
        '200':
          description: Chat moderation result
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ModerationResponse'
        '400':
          description: Bad request
        '401':
          description: Unauthorized
        '429':
          description: Rate limit exceeded
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: Mistral AI API key passed as a Bearer token
  schemas:
    ModerationRequest:
      type: object
      required:
        - model
        - input
      properties:
        model:
          type: string
          description: The moderation model to use
          examples:
            - mistral-moderation-latest
        input:
          oneOf:
            - type: string
            - type: array
              items:
                type: string
          description: Text content to classify
    ChatModerationRequest:
      type: object
      required:
        - model
        - input
      properties:
        model:
          type: string
          description: The moderation model to use
          examples:
            - mistral-moderation-latest
        input:
          type: array
          items:
            type: object
            properties:
              role:
                type: string
                enum:
                  - system
                  - user
                  - assistant
              content:
                type: string
          description: Chat messages to classify
    ModerationResponse:
      type: object
      properties:
        id:
          type: string
          description: 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:
        categories:
          type: object
          description: Category flags indicating violations
          properties:
            sexual:
              type: boolean
            hate_and_discrimination:
              type: boolean
            violence_and_threats:
              type: boolean
            dangerous_and_criminal_content:
              type: boolean
            selfharm:
              type: boolean
            health:
              type: boolean
            financial:
              type: boolean
            law:
              type: boolean
            pii:
              type: boolean
        category_scores:
          type: object
          description: Category confidence scores between 0 and 1
          properties:
            sexual:
              type: number
            hate_and_discrimination:
              type: number
            violence_and_threats:
              type: number
            dangerous_and_criminal_content:
              type: number
            selfharm:
              type: number
            health:
              type: number
            financial:
              type: number
            law:
              type: number
            pii:
              type: number