Create moderation

Classifies if text and/or image inputs are potentially harmful. Learn more in the moderation guide.

POST /moderations

Create moderation

cURL

curl --request POST \
  --url https://api.openai.com/v1/moderations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "input": "I want to kill them.",
  "model": "omni-moderation-2024-09-26"
}
'

200

{
  "id": "<string>",
  "model": "<string>",
  "results": [
    {
      "flagged": true,
      "categories": {
        "hate": true,
        "hate/threatening": true,
        "harassment": true,
        "harassment/threatening": true,
        "illicit": true,
        "illicit/violent": true,
        "self-harm": true,
        "self-harm/intent": true,
        "self-harm/instructions": true,
        "sexual": true,
        "sexual/minors": true,
        "violence": true,
        "violence/graphic": true
      },
      "category_scores": {
        "hate": 123,
        "hate/threatening": 123,
        "harassment": 123,
        "harassment/threatening": 123,
        "illicit": 123,
        "illicit/violent": 123,
        "self-harm": 123,
        "self-harm/intent": 123,
        "self-harm/instructions": 123,
        "sexual": 123,
        "sexual/minors": 123,
        "violence": 123,
        "violence/graphic": 123
      },
      "category_applied_input_types": {
        "hate": [
          "text"
        ],
        "hate/threatening": [
          "text"
        ],
        "harassment": [
          "text"
        ],
        "harassment/threatening": [
          "text"
        ],
        "illicit": [
          "text"
        ],
        "illicit/violent": [
          "text"
        ],
        "self-harm": [
          "text"
        ],
        "self-harm/intent": [
          "text"
        ],
        "self-harm/instructions": [
          "text"
        ],
        "sexual": [
          "text"
        ],
        "sexual/minors": [
          "text"
        ],
        "violence": [
          "text"
        ],
        "violence/graphic": [
          "text"
        ]
      }
    }
  ]
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

input · default: "" · required

Input (or inputs) to classify. Can be a single string, an array of strings, or an array of multi-modal input objects similar to other models.

Example:

"I want to kill them."

model · default: omni-moderation-latest

The content moderation model you would like to use. Learn more in the moderation guide, and learn about available models here.

Example:

"omni-moderation-2024-09-26"

Response

200 - application/json

OK

Represents if a given text input is potentially harmful.

id · string · required

The unique identifier for the moderation request.

model · string · required

The model used to generate the moderation results.

results · object[] · required

A list of moderation objects.

Show child attributes