Token Budget / One Request, GPT-5.4 Nano
1,500
tokens total / 1,000 input + 500 output
SYSTEM
HISTORY
RETRIEVED
OUTPUT
System prompt
300 tk
History
400 tk
Retrieved
300 tk
Output
500 tk
Cost per request
input @ $0.20/1M / output @ $1.25/1M
$0.000000
Output tokens cost
6.25x
more than input. Cap
max_tokens
and the cheap segment stays cheap.