The key insight

One model, many sellers

Because open models are just downloadable files, anyone with GPUs can host them, and many do, competing on price, speed, and reliability.

providers hosting the same DeepSeek model on OpenRouter

providers hosting the same Qwen3 235B model

~⅓

of all OpenRouter token volume runs on open-weight models

Same model, different hosts: different hardware, prices, latency, and privacy policies.
So the question stops being "which model?" and becomes "which provider of that model right now?"