DeepSeek R1 — H200 vs Vera Rubin NVL72 Performance per Dollar
Cost per million tokens of H200 (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.
H200 costs $0.23 per million tokens at 51 tok/s/user on DeepSeek R1; we have no Vera Rubin NVL72 benchmark data at this exact target.
At 90 tok/s/user on DeepSeek R1, H200 comes in at $0.43 per million tokens. Vera Rubin NVL72 hasn't been benchmarked at this operating point.
Only H200 has cost data at 129 tok/s/user on DeepSeek R1 — $0.65 per million tokens. Vera Rubin NVL72 is unmeasured at this target. (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): H200 $1.22/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 | H200:$0.226Vera Rubin NVL72:— | H200:$0.431Vera Rubin NVL72:— | H200:$0.648Vera Rubin NVL72:— |
| Concurrency | H200:~54Vera Rubin NVL72:— | H200:~8Vera Rubin NVL72:— | H200:~4Vera Rubin NVL72:— |