Your AI Router Is Trading a 10x Discount for a 2.5x One
Manifest killed its four-tier LLM router after four months and 7,000 users, and the arithmetic explains why: cache reads bill at 10% of base input, so routing an agent step to a model 2.5x cheaper makes it 3.5x more expensive. Route at the session boundary, not the request.
August 1, 2026 · 15 min read