11 safety categories
Checks for hate, hate/threatening, harassment, harassment/threatening, self-harm, self-harm/intent, self-harm/instructions, sexual, sexual/minors, violence, and violence/graphic.
CatalogLatency Typically under 1 second Async false Rate Limit Per API key Max Input A few thousand characters per text
cn8/studio-moderation
Send a piece of text and get back a safety verdict. The service checks the text
Learn more about Text Moderation Text NLPsyncInstant previewtextanalysismoderation
Input
string
The text to moderate.
Instant sample preview — no cost, no account. Sign up free to run with your own input.
Result
Completed Instant previewJson
{
"flagged": true,
"categories": {
"harassment": 0.86,
"threat": 0.62,
"hate": 0.04,
"self_harm": 0
},
"action_hint": "review"
}Sample output — generated with “You're completely useless, stop replying to my tickets or you'll regret it.”. Sign in to run your own input.
This request costs 1 credits per item.
Overview
Send a piece of text and get back a safety verdict. The service checks the text against 11 categories — hate, hate/threatening, harassment, harassment/threatening, self-harm, self-harm/intent, self-harm/instructions, sexual, sexual/minors, violence, and violence/graphic — and returns is_safe along with a list of plain-language reasons for anything it flags. Use it to moderate comments and reviews, keep chat safe, or gate user-generated content before it's published.
Key capabilities
Clear safety verdict
Returns is_safe (boolean) plus reasons — a list of human-readable strings explaining each flagged category.
Fast
Text moderation is lightweight; you typically get a result in under a second.
When to use it
Comment and review moderation
Filter or flag user comments, reviews, or forum posts before or after publishing.
Chat safety
Check chat messages in real time for policy violations.
Content pipeline gate
Screen text before further processing — for example, before sending it to a chatbot or text-to-speech.
Input & output
input
A single text to moderate.
JSON body
output
is_safe (boolean) and reasons (array of strings for flagged categories).
JSON
Guides & tips
Safety categories
The service checks for 11 categories:
- hate: Hate speech
- hate/threatening: Threatening hate speech
- harassment: Harassment
- harassment/threatening: Threatening harassment
- self-harm: Self-harm content
- self-harm/intent: Self-harm intent
- self-harm/instructions: Self-harm instructions
- sexual: Sexual content
- sexual/minors: Sexual content involving minors
- violence: Violent content
- violence/graphic: Graphic violence
Using moderation in a pipeline
- Screen user input through moderation before processing it (for example, before sending it to a chatbot or text-to-speech).
- When is_safe is false, block the request or return a friendly message to the user.
- Keep the reasons for audit and compliance.
Fail-safe on flagged content
- Moderation is designed to be safe by default: if a verdict can't be produced, the text is treated as unsafe (is_safe: false) so questionable content never slips through.
Specs
Schema
Request body
textrequiredstringThe text to moderate.
Response
is_safebooleanTrue when nothing is flagged.
reasonsarrayPlain-language reasons for each flagged category (empty when safe).
Pricing
Billed per text moderated.
| Service | Unit | Price |
|---|---|---|
| Text Moderation | item | 1 credits/text |