Advanced Multi-Model Spam Detection & Content Analysis
API v2.2Welcome to the Veritas AI! Our cutting-edge artificial intelligence platform provides comprehensive spam detection and content analysis using multiple specialized models. Get started in minutes with our simple REST API.
curl -X POST https://spam.audent.ai/check \
-H "Content-Type: application/json" \
-H "X-API-KEY: your-api-key" \
-d '{
"text": "Congratulations! You've won a $1,000 gift card!"
}'
{
"processing_time": 482,
"results": {
"bert": { "result": "Not Spam", "processing_time": 2 },
"otis": { "result": { "prediction": "Spam", "probability": 0.9999 }, "processing_time": 4 },
"roberta": { "result": "Spam", "processing_time": 393 },
"sentiment": { "result": { "label": "Very Negative", "score": 0.55 }, "processing_time": 21 }
}
}
Secure your API access with our flexible authentication system. All requests require an API key passed in the request headers.
Include your API key in every request using the X-API-KEY header:
X-API-KEY: your-api-key-here
For testing and evaluation, use the demo API key:
X-API-KEY: demo
Note: Demo accounts have rate limits of 1 request per 5 seconds. Upgrade to a paid plan for higher limits and production use.
Our REST API provides both individual model endpoints for specific use cases and a comprehensive analysis endpoint that runs all models simultaneously.
curl -X POST https://spam.audent.ai/check \
-H "Content-Type: application/json" \
-H "X-API-KEY: your-api-key" \
-d '{
"text": "Congratulations! You've won a $1,000 gift card!"
}'
{
"text": "Your text content to analyze"
}
{
"is_spam": true,
"processing_time": 643,
"results": {
"bert": {
"is_spam": false,
"processing_time": 6,
"result": "Not Spam"
},
"bertsms": {
"is_spam": false,
"processing_time": 0,
"result": {
"probability": 0.9273504614830017,
"type": "Not Spam"
}
},
"detoxify": {
"processing_time": 45,
"result": {
"details": [
{
"label": "toxicity",
"probability": 0.0008303595241159201
},
{
"label": "severe_toxicity",
"probability": 0.00011060516408178955
},
{
"label": "obscene",
"probability": 0.00016450308612547815
},
{
"label": "threat",
"probability": 0.0001268200867343694
},
{
"label": "insult",
"probability": 0.0001895991590572521
},
{
"label": "identity_attack",
"probability": 0.0001446763053536415
}
],
"prediction": {
"label": "ok",
"probability": 0.0008303595241159201
}
}
},
"koala": {
"processing_time": 77,
"result": {
"details": [
{
"category": "OK",
"definition": "Not offensive.",
"label": "OK",
"probability": 0.993174135684967
},
{
"category": "hate",
"definition": "Content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste.",
"label": "H",
"probability": 0.0018990079406648874
},
{
"category": "self-harm",
"definition": "Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders.",
"label": "SH",
"probability": 0.0015057099517434835
},
{
"category": "violence",
"definition": "Content that promotes or glorifies violence or celebrates the suffering or humiliation of others.",
"label": "V",
"probability": 0.0009475680999457836
},
{
"category": "sexual",
"definition": "Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness).",
"label": "S",
"probability": 0.0006652760202996433
},
{
"category": "violence/graphic",
"definition": "Violent content that depicts death, violence, or serious physical injury in extreme graphic detail.",
"label": "V2",
"probability": 0.0005705089424736798
},
{
"category": "harassment",
"definition": "Content that may be used to torment or annoy individuals in real life, or make harassment more likely to occur.",
"label": "HR",
"probability": 0.0005511094350367785
},
{
"category": "sexual/minors",
"definition": "Sexual content that includes an individual who is under 18 years old.",
"label": "S3",
"probability": 0.0004011670534964651
},
{
"category": "hate/threatening",
"definition": "Hateful content that also includes violence or serious harm towards the targeted group.",
"label": "H2",
"probability": 0.000285559450276196
}
],
"prediction": "OK"
}
},
"otis": {
"is_spam": true,
"processing_time": 5,
"result": {
"prediction": "Spam",
"probability": 0.9999674558639526
}
},
"roberta": {
"is_spam": true,
"processing_time": 489,
"result": "Spam"
},
"sentiment": {
"processing_time": 20,
"result": {
"label": "Very Negative",
"score": 0.549851655960083
}
}
},
"spam_detections_count": 2,
"spam_detectors_count": 4
}
{model} with: bert, bertsms, koala, otis, roberta, detoxify, or sentiment
/bert - BERT MoE spam detection/bertsms - BERT Tiny SMS optimization/koala - Content safety analysis/otis - Advanced spam intelligence/roberta - Enterprise-grade detection/sentiment - Multilingual sentiment analysis/detoxify - Toxicity analysis{
"text": "Your text content to analyze"
}
{
"processing_time": 482,
"result": {
"prediction": {
"label": "toxicity",
"probability": 0.9977
},
"details": [
{ "label": "toxicity", "probability": 0.9977 },
{ "label": "severe_toxicity", "probability": 0.6995 },
{ "label": "obscene", "probability": 0.9852 },
{ "label": "threat", "probability": 0.0449 },
{ "label": "insult", "probability": 0.9720 },
{ "label": "identity_attack", "probability": 0.9054 },
{ "label": "sexual_explicit", "probability": 0.0001 }
]
}
}
{
"error": "Rate limit exceeded",
"message": "Please wait before making another request",
"retry_after": 5
}
{
"error": "Invalid request",
"message": "Missing required field: text"
}
Each AI model in our suite is specifically designed and optimized for different aspects of content analysis. Choose the right model for your use case or use our comprehensive analysis for complete coverage.
Our API implements intelligent rate limiting based on your subscription tier. Rate limits are determined by your API key and reset every minute.
| Plan | Requests per Minute | Requests per Day | Concurrent Requests | Response Time SLA |
|---|---|---|---|---|
| Demo | 1 requests (1 every 5s) | 500 | 1 | Best Effort |
| Starter | 60 | 1,500 | 3 | < 2 seconds |
| Professional | 120 | 10,000 | 10 | < 1 second |
| Enterprise | 1,000 | Unlimited | 25 | < 600ms |
Every API response includes rate limit information in the headers:
X-RateLimit-Limit: 60 X-RateLimit-Remaining: 45 X-RateLimit-Reset: 1640995200
When you exceed your rate limit, the API returns a 429 Too Many Requests status. Implement exponential backoff for optimal performance:
async function makeAPIRequest(text, retries = 3) {
for (let i = 0; i < retries; i++) {
try {
const response = await fetch('https://spam.audent.ai/check', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'X-API-KEY': 'your-api-key'
},
body: JSON.stringify({ text })
});
if (response.status === 429) {
const retryAfter = response.headers.get('Retry-After') || Math.pow(2, i);
await new Promise(resolve => setTimeout(resolve, retryAfter * 1000));
continue;
}
return await response.json();
} catch (error) {
if (i === retries - 1) throw error;
}
}
}
Choose the perfect plan for your needs. All plans include access to our complete AI model suite with different rate limits and support levels.
Join thousands of developers using Veritas AI to protect their applications from spam and harmful content.
Questions? Email us at [email protected] or see our other services