By margin you mean how much money they're losing on each request to stay ahead of the curve while investments are still flowing?
I don't know, the CEO of Anthropic has openly said that each model by itself is profitable, they just reinvest everything into training more and more expensive models.
you think they're doing inference at a loss even with the API prices?
I don't know, the CEO of Anthropic has openly said that each model by itself is profitable, they just reinvest everything into training more and more expensive models.