Model Routing Is Becoming an Eval-Calibration Problem, Not a Design Choice
Cost reductions in production agents are increasingly the output of a trace-mining and eval-calibration pipeline, not an architectural decision made up front.
By the Editors · 5 min read
The week ending August 29, 2026 produced three pieces of evidence that the routing decision — which model handles which sub-task inside an agent — is no longer being made at design time. It's being discovered by pipelines that mine production traces, build synthetic environments from them, and search for the minimum-cost model-harness configuration that still passes evals. The interesting part isn't that routing matters. It's that routing has stopped being a decision and become a measurement.
Unify's CTO described cutting agent costs 90-95% in two weeks. The specifics are worth reading — a 15 req/s ceiling on OpenAI's prompt cache, subagents demoted to plain function calls, LLM judges forced onto a different model family to avoid self-preference bias. But the underlying method is a search over configurations against a fixed eval suite, not a redesign.