DeepSeek R1 · Performance per Dollar
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. 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.
Near the low end of the 32–122 tok/s/user interactivity band — at 54 tok/s/user — GB200 NVL72 runs $0.082 per million tokens on DeepSeek R1 while H100 runs $0.59. GB200 NVL72 is the cheaper choice by 86%.
On DeepSeek R1 at 77 tok/s/user, the per-million math comes out to $0.091 for GB200 NVL72 and $1.45 for H100; GB200 NVL72 delivers 16× the total tokens per dollar.
At 100 tok/s/user on DeepSeek R1, GB200 NVL72 costs $0.11 per million tokens; H100 costs $2.18. GB200 NVL72 delivers 20× the tokens per dollar 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): GB200 NVL72 $1.86/chip/hr · H100 $1.17/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollars per Million Tokens | GB200 NVL72$0.082H100$0.59 | GB200 NVL72$0.091H100$1.45 | GB200 NVL72$0.11H100$2.18 |
| Concurrency | GB200 NVL72~1,554H100~95 | GB200 NVL72~588H100~31 | GB200 NVL72~333H100~16 |
