Factory Router cuts inference costs 63% in production; dynamic routing squeezes token prices

matanSF · x · 2026-09-25

Factory AI says Factory Router now cuts inference costs by 63% in production, up from 42% in late June, while routed session volume grew roughly 4x.

Commentator matanSF argues dynamic model routing creates a more efficient free market across providers: for any given task, whoever fails to offer the best/fastest/cheapest tokens loses that traffic to a competitor — putting persistent pricing pressure on every model vendor.

Original post →

More from Infra

Infra channel →