Per-token costs don't mean the model is actually cheaper for your work. In almost all of our tests, "cheaper" per-token models like GLM 5.3 and Kimi K3 were *more* expensive than models like GPT 6.1…

Model routers and evals go hand-in-hand - router decisions should be based on evals, and you need to eval different models/harnesses within the exact (or very similar) environments that your agents…