DeepSeek R1 — H100 vs Vera Rubin NVL72 Performance per Dollar
Cost per million tokens of H100 (NVIDIA Hopper) versus Vera Rubin NVL72 (NVIDIA Vera Rubin) on DeepSeek R1. Large-hyperscaler-volume ownership TCO normalized by total tokens — performance per dollar across LLM workloads. Pick the more cost-efficient SKU at every target interactivity level. Use the chart controls below to switch sequences, precisions, and metrics — same interactions as the main inference chart.
Only H100 has cost data at 45 tok/s/user on DeepSeek R1 — $0.44 per million tokens. Vera Rubin NVL72 is unmeasured at this target.
H100 costs $1.16 per million tokens at 71 tok/s/user on DeepSeek R1; we have no Vera Rubin NVL72 benchmark data at this exact target.
At 97 tok/s/user on DeepSeek R1, H100 comes in at $2.11 per million tokens. Vera Rubin NVL72 hasn't been benchmarked at this operating point. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): H100 $1.17/chip/hr · Vera Rubin NVL72 $3.61/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | H100:$0.439Vera Rubin NVL72:— | H100:$1.158Vera Rubin NVL72:— | H100:$2.106Vera Rubin NVL72:— |
| Concurrency | H100:~132Vera Rubin NVL72:— | H100:~41Vera Rubin NVL72:— | H100:~17Vera Rubin NVL72:— |