← Explore

Posts tagged with inference-economics

GPU Economics · ·5 min read

3.5 Gigawatts of Not-Nvidia

Anthropic just told us where the inference money is going, and it's not where most people expected.

tpugoogle-ironwoodanthropic
GPU Economics · ·4 min read

Inference Got 1,000x Cheaper — So Why Is Everyone Spending More?

Three years ago, running a GPT-4-class model cost roughly 20 per million tokens. Today the same caliber of output runs at 0.

inference-economicscost-per-tokenblackwell
← Prev 2 / 2