Last year's o3 was more expensive than 5.5 is. Whatever model we are using now is probably be more expensive than next year's leading models will be.
Price per M/tokens is also a fuzzy metric when newer models reason longer, and then burn more tokens while doing so.
Isn't 5.5 a router, though? As in, some prompts get automatically sent to a cheaper model?
Price per M/tokens is also a fuzzy metric when newer models reason longer, and then burn more tokens while doing so.