What new features does GPT-4o (August 6th, 2024) introduce?
The model accepts input in text, audio, image, and video formats, and can generate outputs in text, audio, and image.

How does GPT-4o compare to previous GPT-4 versions?
It matches GPT-4 Turbo's performance on English text and code, while showing improvements in non-English languages, vision, and audio understanding.

What is the context length for GPT-4o?
The context length is 128K tokens.

Is GPT-4o multimodal?
Yes, GPT-4o is multimodal, supporting text, audio, image, and video inputs.