§ feed · storyline

Upgrading the Moderation API with our new multimodal moderation model

OpenAI upgrades its Moderation API with a new GPT-4o-based multimodal model that improves detection of harmful text and images for developers.

Sep 26 · 12:00:00 · primary fetch1 sourceupdated Sep 26 · 12:00:00

We’re introducing a new model built on GPT-4o that is more accurate at detecting harmful text and images, enabling developers to build more robust moderation systems.

read full article on openai.com ↗

§ sources1 publication · timeline below

openai.comUpgrading the Moderation API with our new multimodal moderation modelprimary12:00:00