Product
Detection API
Send text, get the result back as JSON, with each sentence labeled and the model and run named.
Verify through the API
Pro, Max and Education accounts can make a key in the app and call the verification endpoint. A response says verified only when its verification status is verified_human, and it names each model and run that read the text.
API and MCP helpOne endpoint
POST the text, a setting and, if you want the humanizer model, a model to /api/v1/detect. The response carries the verdict, each sentence with its label, and the detector run that produced the reading.
Not scored under 50 words
Our detector does not score text under 50 words, and readings under 150 words are weak. Check for that before you read a verdict. The first check after a quiet spell can take longer.
Three settings
Changing the setting never turns an AI verdict into Human. It only moves the line for papers that are partly machine-written.
- "standard" flags above 6% and is the default
- "accusation-safe" flags above 15% and misses more AI-edited text than the default
- "sensitive" flags above 2% and, on the default model, flagged 1 of 600 human-written papers in the release test, a 95% ceiling of 0.788%
- "model": "humanizer" and "model": "students" run at "standard" only; any other setting with either is refused
Keys and limits
Create a key in the dashboard. It is shown once and lasts 90 days. API use is not billed yet; each key is held to a ceiling on requests and words an hour, and the reference lists both numbers.
- Keys come with the school plan
No fallback
If our detector is unreachable, the response says so. It never returns a reading from a different detector.
What it reads
Our detector reads English academic and student writing. It is not built or tested for other languages or other kinds of writing.
Start with writing you know.
Paste something you wrote and see the result. It is free to start, with 2,000 words a day, or 50 papers a month with a school email.