
AMD's Inference Discount Depends on a GPU You Can't Rent
One of the first multi-vendor serving benchmarks on Kimi K3 puts AMD's MI355X at roughly 1.5x Nvidia B300's tokens per dollar — but that rests on a $2.50/GPU-hour rate you cannot currently buy. At the only purchasable on-demand rates, the gap narrows to 6%.
August 2, 2026 · 14 min read