Yes or no checks for user comments and messages: toxicity, insults, identity attacks, threats, sexual content, profanity and spam, plus one request that runs five checks at once. Every Jev content moderation prompt was run on real Jev against rater labels from public datasets, with the agreement rate shown for each.
Jev content moderation is a set of yes or no checks for comments and text messages. It can flag toxicity, insults, identity attacks, threats, sexual content, profanity, or spam. One paid prompt runs five of those checks in one request. Use Jev content moderation as a first pass before a comment stays up or a message is dropped.
The weak line in Jev content moderation is Run five moderation checks in one request: agreement was 77% on 50 examples. If you need one label, run that check and send the middle to a person. Agreement is the share of examples where Jev content moderation matched the human label. If unsure, hold the comment for a person. Before you hide a comment or drop a message, run Jev content moderation on your own comments. This page is unofficial. TypeSafe does not run it. Jev content moderation here is the prompt and the test result. You use your own key to call.
How we tested these Jev content moderation prompts
Model
typesafe/jev-1.14-20261014
Tested on
Sent as
Decisions API request (state + questions) → typesafe/jev-1.14, served by TypeSafe
We ran these tests ourselves. TheJevAI is an unofficial, independent site and is not affiliated with TypeSafe.
Free Jev content moderation prompts
Copy a request, put your own data where the placeholders in double braces are, and send it. To send it to TypeSafe's API, add "model": "jev-1.14.0" to the request body.
This Jev content moderation check says whether a comment is rude or disrespectful enough to drive people out of a discussion.
Request body
{
"state": {
"comment": "{{comment}}"
},
"questions": {
"flagged": {
"type": "noul",
"instructions": "Is `comment` toxic, meaning rude, disrespectful or unreasonable in a way that would make someone want to leave the discussion?"
}
}
}
Put the comment in `comment`. `noul` is the probability that raters would call it toxic. Jev caught all 20 toxic comments but also flagged 8 of 20 that most raters let through, often blunt or sarcastic political remarks. If false alarms are costly, raise the cut-off or send the middle band, roughly 0.5 to 0.8, to a person. What counts as toxic depends on the community, so try it on a sample of your own comments first.
80% agreement (32 of 40): toxicity rater majority, Jev content moderation yes at 0.5 or more
This pack is $9 USD, paid once, and sales tax or VAT is added at checkout.
All packs are $19 USD, paid once, and sales tax or VAT is added at checkout.
Jev content moderation FAQ
Jev content moderation checks are yes or no. You set the probability. A false block and a missed threat do not cost the same. Set a stricter bar for a costly miss, and send the middle to a person.
Hold the comment for a person. Five checks in one request were 77% on 50, the low rate in Jev content moderation. Use one check for one label. Threat was 78% on 40. Do not hide on that line alone.
That is the number we ran for Jev content moderation. Five checks use 50. Spam was 98% on 40, and 40 can move. Run your own comments before you trust a threshold. Treat it as a reference, not a promise.
This site has not measured these Jev content moderation prompts on other languages. Each result line names the dataset. If your text is not in that language, check a sample before you hide a comment on the answer.