AI Detection API

Analyze text to determine the likelihood it was generated by AI. Get sentence-level scoring, overall confidence percentages, and detailed chunk analysis.

Request Body

Response

{
  "data": {
    "Label": "AI",                   // "AI", "Might be AI", or "Human"
    "AI": 85.9,                      // AI confidence %
    "Human": 14.1,                   // Human confidence %
    "Chunks": ["..."],               // Sentences flagged as AI
    "SentenceScores": [              // Per-sentence AI scores (0-1)
      { "text": "...", "score": 0.57 },
      { "text": "...", "score": 0.22 }
    ],
    "original": "..."                // Original input
  },
  "message": "AI detection results are ready."
}

Response Fields

Code Examples

curl -X POST https://business.phrasly.ai/api/v1/detect \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "Text you want to check for AI..."}'

How AI Detection Scoring Works

The AI Detection API is powered by Phrasly's in-house sentence-level detection model. Each request is segmented into sentences, scored individually by the model, and aggregated into a document-level confidence percentage. Repeated requests for the same sentences are served from a cache, so re-scanning lightly-edited drafts is fast and cheap.

The response includes an overall confidence score (0–100%) for both AI and Human classifications, along with a summary label: "AI", "Might be AI", or "Human". The Chunks array surfaces just the sentences the model flagged as AI, while SentenceScores exposes the raw 0–1 score for every sentence so you can build your own thresholds or heat-maps.

This approach enables precise identification of mixed-authorship documents where only portions of the text may be AI-generated -a common scenario in collaborative writing, editing, and content creation workflows.

Common Use Cases

The AI Detection API serves a broad range of industries and platforms that need reliable, programmatic AI content classification:

• Academic integrity platforms screening student essays and assignments for AI-generated content before grading.
• Publishing and media companies verifying that submitted articles, guest posts, and editorial content are human-authored.
• Content moderation systems flagging AI-generated spam, fake reviews, or synthetic comments at scale.
• SEO and marketing platforms auditing content quality to ensure AI-generated copy meets editorial standards before publication.
• Enterprise compliance teams reviewing internal documents, reports, and communications for AI authorship disclosure requirements.
• SaaS products adding AI transparency features that show users whether content was created by a human or an AI model.

Constraints & Limits