GPT-4o

JSON →
openai multimodal
textimageaudio

Omni model capable of reasoning across text, image, and audio inputs with real-time conversational abilities.

context window 128K tokens
max output 16K tokens
input price $2.5 / 1M tokens
output price $10 / 1M tokens
tool-usejson-modevisionprompt-cachingstreamingcode-generationfunction-calling
releasedMay 2024
knowledge cutoffOct 2023
gpt-4o-2024-05-13
full doc /v1/models/gpt-4o