Meta Llama Guard 3 LLM-based safety classifier for prompts and responses; multiple sizes. 0300 Guardrails & Moderation# classifier# Llama Guard# LLM
Amazon Bedrock Guardrails Centralized, reusable guardrails for prompts and responses across models. 0310 Guardrails & Moderation# AWS# Bedrock# governance
OpenAI Moderation API (omni-moderation-latest) Multimodal moderation for text & images; granular safety categories and flags. 0400 Guardrails & Moderation# API# image# moderation
