POST

/v1/estimate · gpt-5.5

model GPT-5.5priced per tokensource pricing page ↗

field	recorded source
pricing	Source linked above. Source trace `7c679ba1d370b4f455e84534094cfa25c1a6ce2b3c48479fdfbda654aaddda89`

input_tokens number · usage	$5 / 1M
output_tokens number · usage	$30 / 1M
cache_read_tokens number · usage
quote	$55 — input_tokens 1000000 · output_tokens 1000000 · cache_read_tokens 0 base rate; long prompts re-quote