API References

Changelog

Status

Speak to an Expert

Email support

Moderation API

Documentation

Dashboard

Sign up

Analyze images

Explore our guides and examples to integrate Moderation API.

Introduction

Start moderating your content in under 5 minutes

Quickstart

A quick overview of the concepts used in the moderation API.

Concepts

How your quota is calculated and how to check your usage.

Quota usage

Get more quota and features by upgrading your plan

Manage plan

How to add team members to your organization

Manage team

Learn to set up projects and submit content for moderation

Overview

Automated content moderation

Learn to configure a project for your use-case

Creating a project

Adding models

Learn how to configure flagging thresholds for your models.

Flagging thresholds

Manage API key

Manage project API key

Analyze text

Analyze videos

Analyze audio

What are review queues and how do they work?

Review queues

Creating a queue

Creating a new review queue

Going over the basics of how to use review queues

How to use queues

How to use review queues

Learn how to use actions to moderate content and users

Actions

Queue actions

End users

Queue end users

Webhooks

Integrations

Integrating with your application

Inviting moderators

Learn how to handle user flagged content with Moderation API

User flagged content

How to handle user flagged content

Get started with industry-leading models for content moderation

Ready-made models for content moderation

Classifiers overview

Toxicity

Toxicity model

NSFW

NSFW model

Sentiment

Sentiment model

Propriety

Propriety model

Language

Language model

Spam

Spam model

Sexual

Sexual model

Discrimination

Discrimination model

Self harm

Self harm model

Violence

Violence  model

Entity matchers overview

Detect, extract, or hide email addresses in text.

Email

Email matching

Detect, extract, or hide phone numbers in text.

Phone number

Phone number matching

URL matching

Detect, extract, or hide Addresses in text.

Address

Address matching

Name

Name matching

Detect, extract, or hide usernames in text.

Username

Username matching

Profanity

Profanity matching

Word

Word matching

Detect, extract, or hide sensitive numbers in text.

Sensitive number

Sensitive number matching

Wordlists

Image moderation models are used to detect inappropriate content in images.

Image moderation

Video moderation

Audio moderation

Create custom models in the dashboard. Tailored to your specific needs and improve accuracy for special use cases.

Custom models

Learn how to create a custom model using Moderation API

Creating a model

Creating a custom model

Using a model

Using a custom model

Learn how to use the review queue to improve your custom models automatically.

Adaptive model optimization

Learn how to create AI agents to classify your content.

AI Agents

Creating an agent

How to create an AI Agent

Using an agent

Using AI agents

The Moderation API is organized around REST. Our API has predictable resource-oriented URLs, accepts JSON-encoded request bodies, returns JSON-encoded responses, and uses standard HTTP response codes, authentication, and verbs.

Authentication

Get account details

Learn about the error codes and messages that Moderation API returns.

Errors

Learn about API rate limits and how to work with them.

Rate limits

Analyze text with your Moderation API project.

Analyze text.

Analyze image with your Moderation API project

Analyze image

Analyze video with your Moderation API project

Analyze video

Analyze audio with your Moderation API project

Create an action

Get an action

Update an action

Delete an action and all of its webhooks.

Delete an action

List actions

Execute an action on a set of content items in a queue.

Get Started

Account

Automate Moderation

Review Queue Dashboard

Ready-made Models

Custom Models

AI Agents

Analyze images