DeepSeek R1 — GB300 NVL72 vs Vera Rubin NVL72 Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) 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.
GB300 NVL72 ($0.06) and Vera Rubin NVL72 ($0.00) per million tokens at 117 tok/s/user on DeepSeek R1: at least one input is zero, so the gap can't be expressed as a ratio.
At 182 tok/s/user on DeepSeek R1, GB300 NVL72 and Vera Rubin NVL72 register $0.23 and $0.00 per million tokens — one side has missing pricing or throughput, so a like-for-like ratio isn't meaningful here.
GB300 NVL72 ($0.73) and Vera Rubin NVL72 ($0.00) per million tokens at 247 tok/s/user on DeepSeek R1: at least one input is zero, so the gap can't be expressed as a ratio. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): GB300 NVL72 $2.31/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 | GB300 NVL72:$0.062Vera Rubin NVL72:$0.000 | GB300 NVL72:$0.226Vera Rubin NVL72:$0.000 | GB300 NVL72:$0.726Vera Rubin NVL72:$0.000 |
| Concurrency | GB300 NVL72:~485Vera Rubin NVL72:~400 | GB300 NVL72:~84Vera Rubin NVL72:~400 | GB300 NVL72:~19Vera Rubin NVL72:~400 |