Benchmark $/token for a model on vLLM in Chalk Produces a defensible cost-per-token number: serve the model on a GPU, drive it to saturation, confirm the GPU is actually the limiter, then divide authoritative cloud pricing by measured throughput. The order matters. A throughput number without a saturation check is unfalsifiable, and a $/hr figure pulled from a blog post is usually wrong (see step 5). 1. Serve the model returns (publicly reachable) and . Poll — it returns 503 until weights are loaded, then 200. Expect several minutes for a 7B download. GPU selection. Only GPU pools labelled ca…