Choosing which checks run
The options object turns each category on or off, register sets the word-choice rules, and citationStyle picks APA, MLA or Chicago.
Every category is a toggle on the request. Turn off what your product does not show; the pipeline skips that work and the report omits those findings.
{
"text": "…",
"options": {
"plagiarism": true,
"grammarSpelling": true,
"citations": true,
"aiContent": true,
"style": true,
"register": "academic"
},
"citationStyle": "APA"
}Prop
Type
citationStyle (APA, MLA or Chicago, default APA) sets the style the citation findings and their fixes are written in. Each citation issue also carries messageByStyle and fix.byStyle with all three, so a product that lets the user switch styles can do so without a second check.
Common shapes
| Product | Options |
|---|---|
| Plagiarism checker | { "plagiarism": true, "grammarSpelling": false, "citations": false, "aiContent": false, "style": false } |
| AI detector | { "aiContent": true, "plagiarism": false, "grammarSpelling": false, "citations": false, "style": false } |
| Writing assistant | { "grammarSpelling": true, "style": true, "register": "general", "plagiarism": false, "citations": false, "aiContent": false } |
| Academic integrity | all on, citationStyle set to the course's style |
A category that is off costs no extra work, but the meter is per word, not per category: a check costs 150 credits per 250 words whichever checks run.
Prose, code and language
Documents can be prose, source code or both, in any of the supported languages. The pipeline detects each segment's language and searches accordingly; the report's languages and contentType (prose, code, mixed) say what it found. There is nothing to declare on the request.