Sentinel: AI Text Detector

This API provides an forensic AI detector designed to analyze AI text patterns. It determines the likelihood that a piece of text was generated by an AI models or a human.

Note

For the highest accuracy, we recommend passing a minimum of 50 characters of text. Shorter texts may yield inconclusive results.

Endpoint

POST /api/v1/sentinel

Request Parameters

The following parameters are accepted in the request body:

Field	Type	Required	Description
text	string	Yes	The content to analyze.

Request Examples

cURL

curl -X POST https://heavstal.com.ng/api/v1/sentinel \
-H "Content-Type: application/json" \
-H "x-api-key: <YOUR_API_KEY>" \
-d '{"text": "This is the text I want to scan for AI patterns."}'

JavaScript (Fetch)

const response = await fetch('https://heavstal.com.ng/api/v1/sentinel', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'x-api-key': '<YOUR_API_KEY>'
  },
  body: JSON.stringify({
    text: "This is the text I want to scan for AI patterns."
  })
});

const res = await response.json();
console.log(`Verdict: ${res.data.verdict}`);

Heavstal SDK

import { ai } from '@heavstal/api';

const scan = await ai.sentinel("The quick brown fox jumps over the lazy dog.");
console.log(`Score: ${scan.score}% | Verdict: ${scan.verdict}`);

Python

import requests

url = "https://heavstal.com.ng/api/v1/sentinel"
headers = {
    "Content-Type": "application/json",
    "x-api-key": "<YOUR_API_KEY>"
}
payload = {
    "text": "This is the text I want to scan for AI patterns."
}

response = requests.post(url, headers=headers, json=payload)
print(response.json()["data"])

Response Examples

Success Response

{
  "status": "success",
  "creator": "HEAVSTAL TECH",
  "data": {
    "score": 98,
    "verdict": "AI-Generated",
    "analysis": "The text exhibits low perplexity and consistent sentence structure typical of LLMs."
  }
}

Error Response

{
  "status": "error",
  "error": "Text provided is too short for accurate analysis."
}