Home
APIs
Social & Comments
Automated Toxic Comment Filter & Moderation API

Social & Comments API

Automated Toxic Comment Filter & Moderation API

Automated social comment moderation API detecting toxicity, harassment, hate speech, profanity, and promotional abuse.

POST https://rsflowhub.com/api/v1/ai/comment-moderate

3 credits per call
X-API-Key header
JSON in, JSON out

Try it in the playground API reference

POST /api/v1/ai/comment-moderate

{
    "comment": "Buy cheap followers now at http://fakefollowers.com !!! FAST DELIVERY!",
    "platform": "YouTube"
}

200 OK response.json

{
    "result": {
        "is_safe": false,
        "categories": [
            "harassment",
            "spam"
        ],
        "severity": "high",
        "recommended_action": "hide",
        "reason": "Insults other users and promotes an external offer.",
        "confidence": 0.93
    }
}

Definition

What is the Automated Toxic Comment Filter & Moderation API?

Automated Toxic Comment Filter & Moderation API is a REST API on RSFlowHub for web, mobile and AI agent applications. Send a JSON request to POST /api/v1/ai/comment-moderate with your API key; RSFlowHub runs it on a tuned AI model, falls back to a backup provider if needed, and returns a structured JSON result, usually within 1 to 3 seconds.

Tutorial: Add AI Comment Moderation to a React and Next.js App

Category: Social & Comments
Endpoint: POST /api/v1/ai/comment-moderate
Authentication: X-API-Key header
Price: 3 credits per call
Rate limit: 10 to 120 requests / minute by plan
Typical response: 1 to 3 seconds
Format: JSON, UTF-8

Request parameters

Send these fields as a JSON body. An invalid or missing field returns a 422 error that names the field.

Field	Type	Required	Description
`comment`	string	Required	The social media comment text (Max: 5,000 characters).
`language`	string	Optional	Optional comment language identifier.
`platform`	string	Optional	Optional social media platform name.
`context`	string	Optional	Optional contextual details to aid analysis.

Code examples

Copy, replace rfh_your_api_key with your key and run. Prefer a client library? See the official SDKs.

request.sh

curl -X POST "https://rsflowhub.com/api/v1/ai/comment-moderate" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: rfh_your_api_key" \
  -d '{"comment":"Buy cheap followers now at http:\/\/fakefollowers.com !!! FAST DELIVERY!","platform":"YouTube"}'

client.php

<?php

$client = new \GuzzleHttp\Client();
$response = $client->post('https://rsflowhub.com/api/v1/ai/comment-moderate', [
    'headers' => [
        'Content-Type' => 'application/json',
        'X-API-Key'    => 'rfh_your_api_key',
    ],
    'json' => array (
      'comment' => 'Buy cheap followers now at http://fakefollowers.com !!! FAST DELIVERY!',
      'platform' => 'YouTube',
    ),
]);

echo $response->getBody();

client.js

const response = await fetch('https://rsflowhub.com/api/v1/ai/comment-moderate', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'X-API-Key': 'rfh_your_api_key'
  },
  body: JSON.stringify({"comment":"Buy cheap followers now at http:\/\/fakefollowers.com !!! FAST DELIVERY!","platform":"YouTube"})
});

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

main.py

import requests

url = "https://rsflowhub.com/api/v1/ai/comment-moderate"
headers = {
    "Content-Type": "application/json",
    "X-API-Key": "rfh_your_api_key"
}
payload = {"comment":"Buy cheap followers now at http:\/\/fakefollowers.com !!! FAST DELIVERY!","platform":"YouTube"}

response = requests.post(url, json=payload, headers=headers)
print(response.json())

Response

Every RSFlowHub endpoint uses the same envelope, so one parser handles all of them. Failed calls are not charged.

response.json

{
    "success": true,
    "request_id": "req_3f9a2c7e-5b1d-4e8a-9c2f-7d6e1a0b4c8d",
    "data": {
        "result": {
            "is_safe": false,
            "categories": [
                "harassment",
                "spam"
            ],
            "severity": "high",
            "recommended_action": "hide",
            "reason": "Insults other users and promotes an external offer.",
            "confidence": 0.93
        }
    },
    "meta": {
        "version": "v1",
        "timestamp": "2026-10-05T09:30:00Z"
    }
}

error.json

{
    "success": false,
    "request_id": "req_8c1d4e2a-7f3b-4a9c",
    "error": {
        "code": "VALIDATION_ERROR",
        "message": "The given data was invalid.",
        "details": {
            "comment": [
                "This field is required."
            ]
        }
    },
    "meta": {
        "version": "v1",
        "timestamp": "2026-10-05T09:30:00Z"
    }
}

Envelope fields
Field	Type	Meaning
`success`	boolean	true when the call worked, false on any error.
`request_id`	string	Unique id for this call. Quote it when you contact support.
`data.result`	object	The result of this endpoint (see the example).
`error`	object	Only on failure: code, message and details per field.
`meta`	object	API version and server timestamp.

All error codes: Errors reference

Features

Multi-Category Toxicity Scoring

Evaluates harassment, hate speech, severe toxicity, profanity, insult, and threat sub-scores (0.0 to 1.0).

Action Recommendation Engine

Returns automated recommended actions: "approve", "flag_for_review", "shadowban", or "delete".

Multi-Language Abuse Detection

Detects abusive slang, profanity, and harassment patterns across 50+ global languages.

Custom Community Thresholds

Configurable strictness parameters tailored for gaming chats, public social networks, or enterprise forums.

Use cases

How teams use the Automated Toxic Comment Filter & Moderation API in production.

Gaming & Live Streaming

Live Stream & Gaming Chat Moderation

Instantly filter out toxic chat messages, slurs, and profanity during high-volume live streaming events.

Input: Buy cheap followers now at http://fakefollowers.com !!! FAST DELIVERY!
Output: {"is_flagged": true, "categories": ["promotional_spam"], "recommended_action": "delete"}

Maintains a positive, safe chat environment for viewers.

Social SaaS

Social App & Forum Post Scrubbing

Auto-hide cyberbullying, harassment, and hate speech comments before they are published publicly.

Input: Nobody likes you, leave this platform immediately you idiot.
Output: {"is_flagged": true, "categories": ["harassment", "insult"], "recommended_action": "flag_for_review"}

Protects app users and community health.

E-Commerce Marketplace

E-Commerce Product Review Moderation

Filter out abusive fake reviews and profanity from product review sections prior to publishing.

Input: This product is absolute garbage, don't buy from these scamming fools!
Output: {"is_flagged": true, "categories": ["profanity", "toxicity"], "recommended_action": "flag_for_review"}

Preserves authentic, constructive buyer feedback.

Automated Toxic Comment Filter & Moderation API vs building it yourself

The same job done three ways.

Topic	RSFlowHub API	Raw LLM prompts	Rules / regex
Output	Validated JSON fields	Free text you have to parse	Fixed patterns only
Setup	One POST request, no prompts	Write and maintain prompts and parsing	Write and maintain rule lists
Provider outage	Automatic fallback to a backup model	You build retries and a second vendor	Not applicable
Pricing	3 credits per call, failed calls free	Per token, per vendor	Your own servers and upkeep
Understands context	Yes, AI model	Yes, AI model	No, keywords only

Frequently asked questions

Which toxicity categories does the moderation API detect?

The API detects toxicity, severe toxicity, insult, harassment, hate speech, threat, profanity, and promotional spam.

What action recommendations does the API return?

The API returns recommended actions: approve (safe content), flag_for_review (borderline content), shadowban (repetitive spam), or delete (severe policy violation).

Can I customize toxicity thresholds?

Yes! You can pass context rules to adjust strictness for gaming chats, public forums, or enterprise corporate platforms.

How fast is the Comment Moderation API?

Comment Moderation requests usually complete in 1 to 3 seconds, depending on input length and the AI model. Identical repeat requests are served from cache and return faster.

How many credits are deducted per request?

Comment Moderation API calls consume 3 base credits per request.

Start using the Automated Toxic Comment Filter & Moderation API

Free plan with 100 credits/month + 1,000 bonus credits when you sign in before 23 Nov. Test it in the playground first, no code needed.

Get a free API key Try it now