GPT-4o (fine-tuned, August 2024)

JSON →
openai multimodal
textimageaudio

Fine-tuned version of GPT-4o from August 2024, OpenAI's flagship multimodal model with vision and audio capabilities.

context window 128K tokens
max output 16K tokens
input price $2.5 / 1M tokens
output price $10 / 1M tokens
tool-usejson-modevisionprompt-cachingstreamingcode-generationfunction-callingfine-tunable
releasedAug 2024
knowledge cutoffOct 2023