Why does the production model merge vision with the base turbo model such that the output tokens remains 2048 instead of 4096?
Because if we are using just text, why is the extra output size reduced still?
Because if we are using just text, why is the extra output size reduced still?
https://platform.openai.com/playground/chat?model=gpt-4-turb...
Edit (4:57 ET): "gpt-4-turbo" shows the updated 4096 in playground. "gpt-4-turbo-2024-04-09" remains 2048 in playground.