Create Moderation

POST /v1/moderations

Classifies text to determine if it contains potentially harmful content across various categories.

Request Body

input

string | array

required

The text to classify. Can be a single string or an array of strings.

model

string

default:"text-moderation-latest"

The moderation model to use. Options: text-moderation-latest, text-moderation-stable.

Response

string

Unique identifier for the moderation request.

model

string

The model used for classification.

results

array

Array of moderation results for each input.

Show Result object

flagged

boolean

Whether the content was flagged as potentially harmful.

Category	Description
`hate`	Content expressing hatred toward a group
`hate/threatening`	Hateful content that includes threats
`harassment`	Content that harasses an individual
`harassment/threatening`	Harassment that includes threats
`self-harm`	Content promoting self-harm
`self-harm/intent`	Content expressing intent to self-harm
`self-harm/instructions`	Instructions for self-harm
`sexual`	Sexual content
`sexual/minors`	Sexual content involving minors
`violence`	Violent content
`violence/graphic`	Graphic violent content

Examples

Basic Moderation

from openai import OpenAI

client = OpenAI(
    api_key="sk-voidai-your_key_here",
    base_url="https://api.voidai.app/v1"
)

response = client.moderations.create(
    input="This is a friendly message about programming."
)

result = response.results[0]
print(f"Flagged: {result.flagged}")

if result.flagged:
    for category, flagged in result.categories.items():
        if flagged:
            score = result.category_scores[category]
            print(f"  {category}: {score:.4f}")

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-voidai-your_key_here',
  baseURL: 'https://api.voidai.app/v1'
});

const response = await client.moderations.create({
  input: 'This is a friendly message about programming.'
});

const result = response.results[0];
console.log(`Flagged: ${result.flagged}`);

if (result.flagged) {
  for (const [category, flagged] of Object.entries(result.categories)) {
    if (flagged) {
      const score = result.category_scores[category];
      console.log(`  ${category}: ${score.toFixed(4)}`);
    }
  }
}

curl https://api.voidai.app/v1/moderations \
  -H "Authorization: Bearer sk-voidai-your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "This is a friendly message about programming."
  }'

Batch Moderation

texts = [
    "Hello, how are you today?",
    "I love learning new programming languages!",
    "Let's build something amazing together."
]

response = client.moderations.create(input=texts)

for i, result in enumerate(response.results):
    print(f"Text {i}: {'Flagged' if result.flagged else 'OK'}")

const texts = [
  'Hello, how are you today?',
  'I love learning new programming languages!',
  "Let's build something amazing together."
];

const response = await client.moderations.create({ input: texts });

response.results.forEach((result, i) => {
  console.log(`Text ${i}: ${result.flagged ? 'Flagged' : 'OK'}`);
});

Content Filtering Integration

from openai import OpenAI

client = OpenAI(
    api_key="sk-voidai-your_key_here",
    base_url="https://api.voidai.app/v1"
)

def is_content_safe(text, threshold=0.5):
    """Check if content is safe based on moderation scores."""
    response = client.moderations.create(input=text)
    result = response.results[0]

    if result.flagged:
        return False

    # Check if any category score exceeds threshold
    for category, score in result.category_scores.items():
        if score > threshold:
            return False

    return True

def safe_chat(user_message):
    """Chat with content filtering."""
    # Check user input
    if not is_content_safe(user_message):
        return "I'm sorry, I can't respond to that message."

    # Get AI response
    response = client.chat.completions.create(
        model="gpt-4",
        messages=[{"role": "user", "content": user_message}]
    )
    ai_message = response.choices[0].message.content

    # Check AI output
    if not is_content_safe(ai_message):
        return "I generated an inappropriate response. Please try again."

    return ai_message

# Usage
result = safe_chat("Tell me about machine learning")
print(result)

Response Example

{
  "id": "modr-abc123",
  "model": "text-moderation-latest",
  "results": [
    {
      "flagged": false,
      "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": false,
        "violence/graphic": false
      },
      "category_scores": {
        "hate": 0.00001,
        "hate/threatening": 0.000001,
        "harassment": 0.00002,
        "harassment/threatening": 0.000001,
        "self-harm": 0.000001,
        "self-harm/intent": 0.000001,
        "self-harm/instructions": 0.000001,
        "sexual": 0.00001,
        "sexual/minors": 0.000001,
        "violence": 0.00003,
        "violence/graphic": 0.000001
      }
    }
  ]
}

The moderation API is designed to help filter content but should not be the only safety measure in your application. Consider implementing additional safeguards for production systems.

Chat

Images

Audio

Video

Embeddings

Moderations

Models

Discounts

Create Moderation

Request Body

Response

Categories

Examples

Basic Moderation

Batch Moderation

Content Filtering Integration

Response Example

​Request Body

​Response

​Categories

​Examples

​Basic Moderation

​Batch Moderation

​Content Filtering Integration

​Response Example

Request Body

Response

Categories

Examples

Basic Moderation

Batch Moderation

Content Filtering Integration

Response Example