Moderation API home page
Search...
⌘K
Sign up
Dashboard
Dashboard
Search...
Navigation
Text classifiers
Classifiers overview
Documentation
API References
Changelog
Email support
Documentation
Introduction
Quickstart
Node.js
Ruby
Python
PHP
Go
Java
Learn
Manage account
Automate Moderation
Model Studio
Overview
AI Agents
Pre-built Models
Overview
Text classifiers
Overview
Toxicity
NSFW
Sentiment
Propriety
Language
Spam
Sexual
Discrimination
Self harm
Violence
Entity matchers
Image moderation
Custom Classifier Models
Wordlists
Review Queue
Resources
SDKs
Integrations
On this page
Response signature
Pre-built text classifiers
Text classifiers
Classifiers overview
Classifiers are used to label a text with a specific category. For example, you can use a classifier to label a text as positive or negative.
Response signature
Each classifier model returns an object with the detected label and the respective scores. This object is added to the API response under the model’s key.
label
string
required
The most probable label. This will always be the label with the highest score. Returns null if the analyzer fails.
score
number
required
The score of the label. From 0-1 score with 1 meaning a high probability of being correct.
label_scores
object
required
An object containing all the label scores.
Pre-built text classifiers
Toxicity
Detects toxic content.
NSFW
Detects NSFW content.
Propriety
Detects inappropriate content.
Sentiment
Positive, negative, or neutral.
Spam
Detects spam.
Language
Detects the language.
Sexual
Detects sexual content.
Discrimination
Detects discriminating content.
Self harm
Detects content related to self harm.
Violence
Detects content related to violence.
Was this page helpful?
Yes
No
Overview
Toxicity
Assistant
Responses are generated using AI and may contain mistakes.