Topic in Value
Pricing
-
Deep dive · 6 parts
What a token really costs
The price per million tokens is the least useful number on an AI bill.
-
Part of What a token really costs
Output costs more than input
Every major model charges several times more for a token it generates than for a token you send it.
-
Part of What a token really costs
Caching makes repeated context cheap
On Claude Opus 5.5 an input token read from the cache costs a twentieth of a fresh one, which cut the input bill for this site's build by 92%.
-
Part of What a token really costs
You pay for thinking you never see
More than two thirds of the output tokens in this site's build were thinking, paid for at the output price and mostly never shown.
-
Part of What a token really costs
A token isn't a fixed amount of text
The same paragraph is 59 tokens to GPT-5 and 81 to Claude Opus 5.5, so prices per million tokens don't compare directly.
-
Part of What a token really costs
The cheapest token isn't the cheapest task
Claude Sonnet 5.5's list prices are half of Opus 5.5's, yet the same benchmark tasks cost 28% more to run on Sonnet.