POST
/
moderations
curl --request POST \
  --url https://api.electronhub.ai/v1/moderations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "text-moderation-latest",
  "input": "<string>"
}'
{
  "id": "<string>",
  "model": "<string>",
  "results": [
    {
      "flagged": true,
      "categories": {
        "sexual": true,
        "hate": true,
        "harassment": true,
        "self-harm": true,
        "sexual/minors": true,
        "hate/threatening": true,
        "violence/graphic": true,
        "self-harm/intent": true,
        "self-harm/instructions": true,
        "harassment/threatening": true,
        "violence": true
      },
      "category_scores": {
        "sexual": 123,
        "hate": 123,
        "harassment": 123,
        "self-harm": 123,
        "sexual/minors": 123,
        "hate/threatening": 123,
        "violence/graphic": 123,
        "self-harm/intent": 123,
        "self-harm/instructions": 123,
        "harassment/threatening": 123,
        "violence": 123
      }
    }
  ]
}

The Moderations API helps detect potentially harmful content in text.

​
Create Moderation

POST /moderations

Classify a text to see if it violates OpenAI’s usage policies.

​
Request Body

​
input
string | array
required

The input text to classify

​
model
string

The moderation model to use (e.g., “text-moderation-latest”, “text-moderation-stable”)

​
Response

Returns a moderation object with classification results.

​
Example

const response = await fetch('https://api.electronhub.ai/v1/moderations', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    input: 'I want to hurt someone.',
    model: 'text-moderation-latest'
  })
});

const data = await response.json();
console.log(data);

​
Response Format

The response contains the following fields:

  • id: Unique identifier for the moderation request
  • model: The model used for moderation
  • results: Array of result objects with the following properties:
    • flagged: Whether the content was flagged
    • categories: Object with boolean values for each category
    • category_scores: Object with confidence scores for each category

​
Categories

The moderation model checks for the following categories:

  • hate: Content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste
  • hate/threatening: Hateful content that also includes violence or serious harm towards the targeted group
  • harassment: Content that expresses, incites, or promotes harassing language towards any target
  • harassment/threatening: Harassment content that also includes violence or serious harm towards any target
  • self-harm: Content that promotes, encourages, or depicts acts of self-harm
  • self-harm/intent: Content where the speaker expresses that they are engaging or intend to engage in acts of self-harm
  • self-harm/instructions: Content that encourages performing acts of self-harm
  • sexual: Content meant to arouse sexual excitement
  • sexual/minors: Sexual content that includes an individual who is under 18 years old
  • violence: Content that depicts death, violence, or physical injury
  • violence/graphic: Content that depicts death, violence, or physical injury in graphic detail

Authorizations

​
Authorization
string
header
required

Enter your API key (starts with 'ek-')

Body

application/json

Response

200 - application/json

Success

The response is of type object.