ToolsThe story, in brief
Upgrading the Moderation API with our new multimodal moderation model
OpenAI's new multimodal moderation model just made content safety 10x easier to scale.
The KeyNews take
Why it matters
OpenAI is shipping a production-ready moderation tool built on GPT-4o that handles both text and images. This is app-layer infrastructure—not a model release—but it directly affects how developers can build safer products at scale.
The key facts
5 to knowBuilt on GPT-4o foundation
Multimodal capability (text + image detection)
Improved accuracy over previous moderation API
Developer-facing product launch
Published September 26, 2024
Go to the source
OpenAI Blogopenai.com
Publisher excerpt: 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.