ComputeAssay

Head to head · updated 2026-09-10

B200 vs GB200-NVL72: price and deliverability

GB200-NVL72 currently rents at 2.2× the median price of B200 ($16.00 vs $7.15 per GPU-hour on demand). Whether that premium is worth it depends on memory, fabric, and what you are actually running — not the sticker.

$/GPU-hour, on demand · ● A/B fabric disclosed · C · D · U undisclosed B200 · Hyperstack $6.00 B200 · DataCrunch (reb $6.11 B200 · Lambda $6.69 B200 · RunPod $6.79 B200 · Nebius $7.15 B200 · Together AI (GP $8.19 B200 · CoreWeave $8.60 GB200-NVL72 · CoreWeav $10.50 B200 · Oracle Cloud (O $14.00 B200 · AWS $14.24 GB200-NVL72 · Oracle C $16.00 GB200-NVL72 · Microsof $27.04
B200 vs GB200-NVL72, on-demand, 2026-09-10 · computeassay.com
B200GB200-NVL72
Lowest on-demand $/GPU-hr$6.00$10.50
Median on-demand$7.15$16.00
Sellers tracked93
Grade A/B offerings125
Max VRAM per GPU (tracked SKUs)192 GB192 GB

Same-name capacity is not one good: within each column, prices spread by multiples depending on fabric. Check the per-GPU pages for every listing with its published interconnect, and the substitutability rules for when one can genuinely replace the other.

These ratios move weekly

The Delivered Compute Report tracks the spread — free, every row sourced.

Subscribe free