The inference cost curve is flattening, and that changes plans
Price per token has stopped halving every few months. Budgets built on that assumption need revisiting.
The easy gains from better kernels and batching are mostly banked. What remains is memory bandwidth and interconnect.
Subscriber story
Continue reading with a subscription
This piece is part of the subscriber archive. Subscribe to the daily brief for full access — one email, no card, cancel any time.
Already a subscriber?
#inference#economics#infrastructure
More in this section
🔒aiSubscriber
Why small models are winning on-device
Four-bit quantization plus better distillation is making 3B models genuinely useful in production.
ai
Synthetic data is hitting a wall nobody wants to name
Model collapse is real, but the more immediate problem is boring: attribution and licensing.
🔒aiSubscriber
The open-weights licence split is becoming permanent
Two families of licence, two incompatible expectations, and a lot of downstream confusion.