DeepSeek R1 — GB300 NVL72 vs H100 Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus H100 (NVIDIA Hopper) on DeepSeek R1. Owning-hyperscaler TCO normalized by output 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.
On DeepSeek R1 at 40 tok/s/user, the per-million math comes out to $0.09 for GB300 NVL72 and $1.34 for H100; GB300 NVL72 delivers 1314% more output per dollar.
At 70 tok/s/user on DeepSeek R1, GB300 NVL72 costs $0.14 per million tokens; H100 costs $4.65. GB300 NVL72 is 3312% more cost-efficient at this operating point.
GB300 NVL72 edges H100 at 99 tok/s/user on DeepSeek R1 — $0.30 per million tokens versus $15.6, a 5167% cost-per-token gap. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
GPU pricing (owning hyperscaler): GB300 NVL72 $2.65/GPU/hr · H100 $1.30/GPU/hr. Source: SemiAnalysis Market August 2025 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:$0.095H100:$1.339 | GB300 NVL72:$0.136H100:$4.655 | GB300 NVL72:$0.297H100:$15.632 |
| Concurrency | GB300 NVL72:~2869H100:~605 | GB300 NVL72:~959H100:~57 | GB300 NVL72:~571H100:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.