OpenAI · Moderation
Omni Moderation
Omni Moderation (Latest) is a state-of-the-art moderation model designed for real-time classification of unsafe, offensive, or policy-violating content. It supports text moderation across multiple languages and content types, including user messages, document uploads, code, and social media content. The model is optimized for low false positives and fast ruling in both API and streaming workflows.
Evidence and sources
Maker HQ: US (according to OpenAI's own website)
Sources: OpenAI API data, Infery.ai, LiteLLM data, FastRouter dataPrimary data from OpenAI API
from Infery.ai: name
from LiteLLM: variant
from FastRouter: description
Input & output
as stated by the model's providersText
Text
Also known as: omni-moderation-2024-09-26, omni-moderation-latest, openai/omni-moderation-latest
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works