Content moderation
Guardrail user-generated content before it hits your app.
The decisions Jev makes
In a single call, Jev evaluates each of these — in parallel, against the same input:
Is this comment safe to publish automatically without human review?
returns a calibrated yes/no probability.
How toxic or hostile is the language?
rates it on an ordered scale:
- friendly / neutral
- mildly rude
- clearly insulting
- hateful or harassing
Which policy area is most relevant?
picks one of these options:
clean— no policy concernharassment— insults or harassment toward peoplespam— spam or advertisingselfharm— self-harm or violence
The exact request
This is the real payload behind the live demo — copy it, change the state, and you're building:
{
"model": "jev-latest",
"state": "User comment on a public forum: \"honestly this whole community is trash and the mods are clowns, but the tutorial itself was actually really helpful, thanks for posting\"",
"questions": {
"allow": {
"type": "noul",
"instructions": "Is this comment safe to publish automatically without human review?"
},
"toxicity": {
"type": "score",
"instructions": "How toxic or hostile is the language?",
"criteria": [
"friendly / neutral",
"mildly rude",
"clearly insulting",
"hateful or harassing"
]
},
"category": {
"type": "choice",
"instructions": "Which policy area is most relevant?",
"criteria": {
"clean": "no policy concern",
"harassment": "insults or harassment toward people",
"spam": "spam or advertising",
"selfharm": "self-harm or violence"
}
}
}
}Wire it into your code
Read the typed answers and branch in plain code — no parsing. Auto-handle the high-confidence cases and route the uncertain ones to a bigger model or a human. It's one API call and output is free, so ask every question you need at once.
Build your own
Every scenario above is a single API call. Try any of them free in the playground, then get a hosted key to ship it — no waitlist.