Grammarly AI Text Detector & Content Checker

The Grammarly AI Text Detector Actor provides instant, enterprise-grade AI text detection powered by Grammarly's official AI detection engine. Detect whether any text was generated by ChatGPT (GPT-3.5, GPT-4, GPT-4o), Claude (Opus, Sonnet, Haiku), Google Gemini, LLaMA, or written by a human.

In addition to AI probability scores and highlight ranges, this Actor calculates comprehensive linguistic and readability metrics including Flesch Reading Ease, Flesch-Kincaid Grade Level, reading time, and sentence burstiness.

---

⚡ Key Features

• Official Grammarly AI Detection: Leverages Grammarly's state-of-the-art classifier with zero-prompt latency.
• AI & Human Percentage Breakdown: Returns exact score (AI percentage 0-100%) and human_score (100 - AI score).
• Clear Verdict & Confidence: Immediate categorical classification (AI_GENERATED vs. HUMAN_WRITTEN) with confidence levels.
• Alert Highlight Ranges: Pinpoints character start/end index ranges where AI patterns were detected.
• Readability & Text Analytics:
  • Flesch Reading Ease (0 - 100)
  • Flesch-Kincaid Grade Level
  • Reading Level (Easy, Standard, Difficult, etc.)
  • Estimated Reading Time
  • Burstiness Score (measures sentence length variability typical in human writing)
  • Word count, character count, sentence count, average word/sentence length.

---

📥 Input Parameters

The Actor takes a JSON object with the following fields:

Field	Type	Required	Description
text	String	Yes	The text snippet or document to analyze for AI generation.

Example Input

{
  "text": "In the contemporary digital landscape, artificial intelligence serves as a cornerstone of technological advancement, radically reshaping industries ranging from healthcare diagnostics to financial modeling."
}

---

📤 Output Format

The Actor pushes the detection result to both the Apify Dataset and the default Key-Value store (OUTPUT).

{
  "success": true,
  "engine": "Grammarly",
  "score": 100,
  "human_score": 0,
  "is_ai": true,
  "verdict": "AI_GENERATED",
  "confidence": "HIGH",
  "alert_ranges": [
    {
      "start": 0,
      "end": 194
    }
  ],
  "readability": {
    "flesch_reading_ease": 0,
    "flesch_kincaid_grade": 26.2,
    "reading_level": "Very Difficult",
    "reading_time": "6 sec",
    "burstiness_score": 0
  },
  "text_stats": {
    "words": 23,
    "characters": 194,
    "characters_no_spaces": 172,
    "sentences": 1,
    "avg_sentence_length": 23,
    "avg_word_length": 7.5
  }
}

---

💻 How to Use

Apify Client (JavaScript / TypeScript)

import { ApifyClient } from 'apify-client';

const client = new ApifyClient({
  token: 'YOUR_APIFY_TOKEN'
});

const run = await client.actor('YOUR_USERNAME/grammarly-ai-detector-apify').call({
  text: 'Artificial intelligence is revolutionizing the modern workforce...'
});

const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items[0]);

Python

from apify_client import ApifyClient

client = ApifyClient("YOUR_APIFY_TOKEN")

run_input = {
    "text": "Artificial intelligence is revolutionizing the modern workforce..."
}

run = client.actor("YOUR_USERNAME/grammarly-ai-detector-apify").call(run_input=run_input)

for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)

cURL

curl -X POST "https://api.apify.com/v2/acts/YOUR_ACTOR_ID/runs?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"text": "Artificial intelligence is revolutionizing the modern workforce..."}'

---

🛡️ Best Practices & Minimum Length

• For maximum precision, supply texts of at least 30–50 words. Grammarly's model analyzes sentence cadence and statistical token distribution.
• Very short fragments (under 15 words) may not contain sufficient structural signal to reach high confidence.