GPU Economics: What Inference Actually Costs in 2026

The question every AI team eventually asks: should we rent GPUs and run models ourselves, or just pay per token through an API? The answer changed a lot in the last six months. GPU rental prices dropped. API prices dropped faster. New GPU generations shipped. And mixture-of-experts models made the whole calculation messier than it used to be. Here's the actual math, with real numbers from real providers. GPU rental prices right now These are on-demand, publicly listed prices as of February 2026. No negotiated enterprise deals, no reserved instances. GPU Provider Config $/hour VRAM (GB) NVIDIA B200 CoreWeave 8x GPU $68.80 180 NVIDIA GB200 NVL72 CoreWeave 4-GPU slice $42.00 186 NVIDIA HGX H200 CoreWeave 8x GPU $50.44 141 NVIDIA HGX H100 CoreWeave 8x GPU $49.24 80 NVIDIA GH200 CoreWeave 1x GPU $6.50 96 NVIDIA A100 80GB CoreWeave 8x GPU $21.60 80 NVIDIA L40S CoreWeave 8x GPU $18.00 48 NVIDIA RTX PRO 6000 CoreWeave 8x GPU $20.00 96 A few things stand out. The B200 costs 40% more than the H1