[jp57]

Honest question: Is inference actually being sold at a loss? I.e. does inference itself cost more to run than we're being charged, or are the companies operating at a loss because they're spending more on training than the margins they get from inference?

[borealis-dev]

Companies like OpenAI and Anthropic are particularly sneaky about reporting numbers, but there's good reason to believe it is: https://www.wheresyoured.at/oai_docs/

[ajam1507]

Even if an AI company spends more on inference than their revenue, that does not mean that they are selling inference at a loss.