alt Hacker NewsAre you sure? I thought tokens (or watts) were sold at such a loss that if current supply limits were reached they’d go broke
Replies
nsvd2 • yesterday at 8:07 PM
These companies are generally profitable for inference but it does not cover the cost of R&D (training).
➕ show 1 reply
The entire marginal cost to serve AI models is paid for by the API costs of all providers by nearly every estimation. The cost not currently recouped is entirely in the training and net-new infrastructure that they're building.