Source: OpenAI engineers earlier this month told some colleagues they had figured out a way to more than halve the cost of inference (Stephanie Palazzolo/The Information)
Get the Tech newsletter
Daily tech — startups, AI labs, chips, the launches that shape the next decade. Free.
- OpenAI engineers told some colleagues earlier this month they had figured out a way to more than halve the cost of inference, per a source reported by The Information's Stephanie Palazzolo.
- The Information framed the claim inside its ongoing coverage of how Anthropic, Google, and OpenAI compete to secure server chips capable of running their models — the chip supply that the cheaper inference would presumably stretch further.
Why it matters: If the engineers' claim holds up, a more-than-50% drop in inference cost would directly cut the per-query expense of running OpenAI's models — a critical margin lever in its pricing competition with Google and Anthropic.
Ask SkimNews
