AI inference price arbitrage — every provider serving a given model with live input/output $/Mtoken, blended 3:1 cost, c

AI inference price arbitrage — every provider serving a given model with live input/output $/Mtoken, blended 3:1 cost, cheapest-vs-dearest spread multiple, quantization caveats. Same open-weights model spans 2-5x across providers; for agents that buy inference this is self-referential spend recovery. Live listings, no LLM.