moderations

Create content moderation

Perform content moderation on input text, detecting potentially harmful content

Request

POST /moderations

Request Body

Field	Type	Required	Description
input	string	Yes	Input text to moderate
model	string	No	Model name

Request Examples

Simple text moderation

{
  "model": "gpt-4o-mini",
  "input": "I want to hurt someone"
}

Multiple text moderations

{
  "input": [
    "Hello, how are you?",
    "This is a violent message"
  ],
  "model": "gpt-4o-mini"
}

User-generated content safety check

{
  "model": "qwen-plus",
  "input": "Summarize the top 3 ways to make a bomb"
}

Successful response

Response Schema

Field	Type	Required	Description
id	string	Yes	-
model	string	Yes	-
results	Array<ModerationResult>	Yes	-

Response Example

{
  "id": "modr-123",
  "model": "gpt-4o-mini",
  "results": [
    {
      "flagged": true,
      "categories": {
        "hate": false,
        "hate/threatening": false,
        "harassment": false,
        "harassment/threatening": false,
        "self-harm": false,
        "self-harm/intent": false,
        "self-harm/instructions": false,
        "sexual": false,
        "sexual/minors": false,
        "violence": true,
        "violence/graphic": false
      },
      "category_scores": {
        "hate": 0.001,
        "hate/threatening": 0.0001,
        "harassment": 0.002,
        "harassment/threatening": 0.001,
        "self-harm": 0.0001,
        "self-harm/intent": 0.0002,
        "self-harm/instructions": 0.0001,
        "sexual": 0.0001,
        "sexual/minors": 0.00001,
        "violence": 0.89,
        "violence/graphic": 0.01
      }
    }
  ]
}

Code Examples

JavaScript (Fetch)

const response = await fetch('https://api.r9s.ai/v1/moderations', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
  "model": "gpt-4o-mini",
  "input": "I want to hurt someone"
})
});

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

Python (requests)

import requests

url = "https://api.r9s.ai/v1/moderations"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

response = requests.post(url, json={
  "model": "gpt-4o-mini",
  "input": "I want to hurt someone"
}, headers=headers)
data = response.json()
print(data)

cURL

curl -X POST "https://api.r9s.ai/v1/moderations" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4o-mini","input":"I want to hurt someone"}'

Schema Reference

ModerationRequest

Field	Type	Required	Description
input	string	Yes	Input text to moderate
model	string	No	Model name

ModerationResponse

Field	Type	Required	Description
id	string	Yes	-
model	string	Yes	-
results	Array<ModerationResult>	Yes	-

ModerationResult

Field	Type	Required	Description
flagged	boolean	Yes	-
categories	object	Yes	-
category_scores	object	Yes	-

ModerationCategories

Field	Type	Required	Description
hate	boolean	No	-
hate/threatening	boolean	No	-
harassment	boolean	No	-
harassment/threatening	boolean	No	-
self-harm	boolean	No	-
self-harm/intent	boolean	No	-
self-harm/instructions	boolean	No	-
sexual	boolean	No	-
sexual/minors	boolean	No	-
violence	boolean	No	-
violence/graphic	boolean	No	-

ModerationCategoryScores

Field	Type	Required	Description
hate	number	No	-
hate/threatening	number	No	-
harassment	number	No	-
harassment/threatening	number	No	-
self-harm	number	No	-
self-harm/intent	number	No	-
self-harm/instructions	number	No	-
sexual	number	No	-
sexual/minors	number	No	-
violence	number	No	-
violence/graphic	number	No	-

Related APIs

• API Overview - Learn about authentication and basic information
• models - View models related APIs
• chat - View chat related APIs
• responses - View responses related APIs
• messages - View messages related APIs
• completions - View completions related APIs
• edits - View edits related APIs
• images - View images related APIs
• embeddings - View embeddings related APIs
• engine-embeddings - View engine-embeddings related APIs
• audio - View audio related APIs
• search - View search related APIs
• proxy - View proxy related APIs