AI Detector API for Humanized Content
Score any text 0 to 100 for AI likelihood with one REST call, and check every humanizer output before it ships.
The StealthGPT AI Detector API is a REST endpoint, POST /api/stealthify/detect, that returns a 0-100 score for how likely a text is to be flagged as AI-generated. It runs the same backend as the free StealthGPT AI Detector, accepts up to 50,000 characters, works in any language, and costs one word per input word.
Humanize, then detect, in one API
Humanize then verify
Send drafts to /api/stealthify, then score the result with /detect for an independent AI check.
One clear score
0-30 is likely human, 31-70 is mixed, and 71-100 is likely AI-generated.
Pay per input word
Each request costs one word per input word, billed from prepaid words or pay-as-you-go.
Works in any language
The detector is language-agnostic, so you can score non-English content with the same call.
Your first detection call
curl --location 'https://www.stealthgpt.ai/api/stealthify/detect' \
--header 'api-token: YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"text": "Renewable energy sources, including solar and wind power, represent inexhaustible resources unlike finite fossil fuels."
}'{
"howLikelyToBeDetected": 87,
"wordsSpent": 16,
"remainingCredits": 984984,
"billingMode": "prepaid",
"meteredChargedCredits": 0
}Example response from the StealthGPT API docs.
Read the docsFrequently Asked Questions
Add AI detection to your pipeline
Tell us about your volume and we'll help you pick the right API plan, or start today from $19 a month.