Remix.run Logo
dktp 4 hours ago

The idea is that smarter models might use fewer turns to accomplish the same task - reducing the overall token usage

Though, from my limited testing, the new model is far more token hungry overall

manmal 4 hours ago | parent [-]

Well you‘ll need the same prompt for input tokens?

httgbgg 3 hours ago | parent [-]

Only the first one. Ideally now there is no second prompt.

manmal 3 hours ago | parent [-]

Are you aware that every tool call produces output which also counts as input to the LLM?