Introducing our new multimodal moderation model: an upgrade to the Moderation API
OpenAI unveils a new multimodal moderation model built on GPT-4o, offering improved detection of harmful text and images. This upgrade to the Moderation API provides developers with a stronger foundation for building robust content moderation systems across multiple content types.
We're unveiling a new model built on GPT-4o that does a better job of spotting harmful text and images, giving developers a stronger foundation for building content moderation systems.
Comments (0)