Llama API
Log in

Get started

Overview
Quickstart

Essentials

Models
API keys
SDKs & libraries
Rate limits

Features

Chat completion
Image understanding
Structured output
Tool calling
OpenAI compatibility
Moderation
Fine-tuning & evaluation

Guides

Chat & conversation
Tool calling
Moderation & security
Best practices

API reference

Chat completion
Models
Moderations

Resources

Data commitments
Legal

Moderations

Llama API offers safeguard models based on Llama Guard that you can use to moderate user input and model output for problematic content.See the moderation & security guide for more details on using this endpoint as part of a safety-conscious application layer.

POST /moderations

Request body

Content Type: application/json

messages
array (one of UserMessage, SystemMessage, AssistantMessage, ToolResponseMessage)
required
messages
model
string
optional
model name

Response

HTTP 200Moderation analysis results

Content Type: application/json

model
string
required
model name
results
array
required
metadata for violation
curl
Python
Python (Llama API client)
Shell
Was this page helpful?
POST /moderations