Why a token is not a standard unit of AI pricing
- Source
- x.com
- Date

On tokens and prices per token. I said I’d write more about this, so here goes: an OpenAI token != another model’s token. We compare AI prices in dollars per million tokens as if a token were a standardized unit, like a gram or a kilowatt-hour. It isn’t. Different models use and produce the exact same text using different numbers of tokens, which means a lower price per token does not necessarily mean a lower bill. Imagine two identical pizzas. One is cut into 8 slices at $2 each. The other is cut into 16 slices at $1.25 each. The second place advertises cheaper slices, but the whole pizza costs $20 instead of $16. Bummer ... your stomach doesn't actually care about the number of slices you just ate. I know you are hungry now, but back to tokens. In one small comparison spanning English, technical, multilingual, and numerical text, the tokenizer we use for GPT-5.6 Sol used 766 tokens versus an estimated 1,170 for Claude Opus 5. That's a very significant difference of about 34.5% fewer tokens. You can get the same exact text, but pay for all those extra tokens. The price per token doesn't really tell this story. Even correcting for tokenizer differences misses the bigger point.…

Context
A lower price per million can still produce a higher bill for the same text. Different models divide text into different numbers of tokens, so comparing their advertised unit prices leaves out how many units each model charges for. Tibo's pricing explanation uses this distinction to argue for comparing the cost of completing a task successfully.
The post's small tokenizer comparison illustrates the accounting issue, but it cannot establish which model is cheaper across all workloads. A useful comparison measures the actual bill alongside whether the model completed the work, rather than treating each provider's token as an identical quantity of text.
- token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
Checking sign-in…
Loading comments…



