Modération

This page contains the endpoints related to content moderation.

Couverture Apifox

• Create moderation requests

API de modèles / Modération

POST Create Moderation

POST /moderations

Classifies whether the input violates OpenAI content policies

Body Parameters

{
    "model": "omni-moderation-latest",
    "input": [
      { "type": "text", "text": "...text to classify goes here..." },
      {
        "type": "image_url",
        "image_url": {
          "url": "https://github.com/dianping/cat/raw/master/cat-home/src/main/webapp/images/logo/cat_logo03.png"
        }
      }
    ]
  }

Request Parameters

Name	In	Type	Required	Description
Authorization	header	string	No	none
body	body	object	No	none
» input	body	string	Yes	Input text to classify.
» model	body	string	Yes	Two moderation models are available: text-moderation-stable and text-moderation-latest. The default, text-moderation-latest, upgrades automatically over time so you always use the most accurate model. If you choose text-moderation-stable, you will receive advance notice before model updates. text-moderation-stable may be slightly less accurate than text-moderation-latest.

Response Example

200 Response

{
  "id": "string",
  "model": "string",
  "results": [
    {
      "categories": {
        "hate": true,
        "hate/threatening": true,
        "self-harm": true,
        "sexual": true,
        "sexual/minors": true,
        "violence": true,
        "violence/graphic": true
      },
      "category_scores": {
        "hate": 0,
        "hate/threatening": 0,
        "self-harm": 0,
        "sexual": 0,
        "sexual/minors": 0,
        "violence": 0,
        "violence/graphic": 0
      },
      "flagged": true
    }
  ]
}

Responses

Status	Meaning	Description	Model
200	OK	none	Inline

Response Schema

Status 200

Name	Type	Required	Constraints	Chinese Name	Description
» id	string	true	none		Unique identifier for the moderation request.
» model	string	true	none		Model used for moderation.
» results	[object]	true	none		Detailed moderation results.
»» categories	object	false	none		All category labels detected by the moderation model.
»»» hate	boolean	true	none		Whether the moderation model detected hateful content.
»»» hate	boolean	true	none		none
»»» self-harm	boolean	true	none		Whether the moderation model detected self-harm content.
»»» sexual	boolean	true	none		Whether the moderation model detected sexual content.
»»» sexual	boolean	true	none		none
»»» violence	boolean	true	none		Whether the moderation model detected violent content.
»»» violence	boolean	true	none		none
»» category_scores	object	false	none		Scores produced by the moderation model for every category label.
»»» hate	number	true	none		Moderation-model score for hateful content.
»»» hate	number	true	none		none
»»» self-harm	number	true	none		Moderation-model score for self-harm content.
»»» sexual	number	true	none		Moderation-model score for sexual content.
»»» sexual	number	true	none		none
»»» violence	number	true	none		Moderation-model score for violent content.
»»» violence	number	true	none		none
»» flagged	boolean	false	none		Whether the moderation model flagged the input as suspicious content.