DeepSeek R1 — GB200 NVL72 vs H100 Performance per Dollar
Cost per million tokens of GB200 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.
Near the low end of the 13–128 tok/s/user interactivity band — at 41 tok/s/user — GB200 NVL72 runs $0.11 per million tokens on DeepSeek R1 while H100 runs $1.35. GB200 NVL72 is the cheaper choice by 1082%.
On DeepSeek R1 at 70 tok/s/user, the per-million math comes out to $0.14 for GB200 NVL72 and $4.65 for H100; GB200 NVL72 delivers 3251% more output per dollar.
At 99 tok/s/user on DeepSeek R1, GB200 NVL72 costs $0.26 per million tokens; H100 costs $15.6. GB200 NVL72 is 5974% more cost-efficient at this operating point. (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): GB200 NVL72 $2.21/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 | GB200 NVL72:$0.114H100:$1.351 | GB200 NVL72:$0.139H100:$4.655 | GB200 NVL72:$0.257H100:$15.632 |
| Concurrency | GB200 NVL72:~3266H100:~584 | GB200 NVL72:~1006H100:~57 | GB200 NVL72:~612H100:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.