ComputeAssay

Head to head · updated 2026-09-10

H100-SXM vs H200-SXM: price and deliverability

H200-SXM currently rents at 1.6× the median price of H100-SXM ($6.20 vs $3.99 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 H100-SXM · Hyperstack $3.20 H100-SXM · DataCrunch $3.25 H100-SXM · RunPod $3.49 H100-SXM · Scaleway $3.61 H100-SXM · Nebius $3.85 H100-SXM · Crusoe $3.90 H100-SXM · Lambda $3.99 H200-SXM · Hyperstack $3.99 H200-SXM · DataCrunch $4.00 H200-SXM · Crusoe $4.29 H200-SXM · Nebius $4.50 H100-SXM · CoreWeave $6.16 H200-SXM · OVHcloud $6.20 H200-SXM · CoreWeave $6.31 H100-SXM · AWS $6.88 H200-SXM · AWS $7.91 H100-SXM · Oracle Clou $10.00 H200-SXM · Oracle Clou $10.00 H200-SXM · Microsoft A $10.60 H100-SXM · Google Clou $11.06 H100-SXM · Google Clou $11.62 H100-SXM · Microsoft A $12.29
H100-SXM vs H200-SXM, on-demand, 2026-09-10 · computeassay.com
H100-SXMH200-SXM
Lowest on-demand $/GPU-hr$3.20$3.99
Median on-demand$3.99$6.20
Sellers tracked129
Grade A/B offerings1613
Max VRAM per GPU (tracked SKUs)80 GB141 GB

Memory is the first gate: H200-SXM carries 141 GB per GPU vs 80 GB. If your model + KV cache does not fit, price is irrelevant — the smaller card is not a substitute at any discount (ASSAY-1 §5).

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