DeepSeek R1 — GB300 NVL72 vs H200 Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus H200 (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.
At 59 tok/s/user on DeepSeek R1, GB300 NVL72 costs $0.12 per million tokens; H200 costs $0.93. GB300 NVL72 is 686% more cost-efficient at this operating point.
GB300 NVL72 edges H200 at 98 tok/s/user on DeepSeek R1 — $0.29 per million tokens versus $2.66, a 832% cost-per-token gap.
Push DeepSeek R1 to 136 tok/s/user and GB300 NVL72 lands at $1.19 per million tokens against H200's $9.94 — GB300 NVL72 pulls ahead by 733%. (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 · H200 $1.41/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:$0.118H200:$0.929 | GB300 NVL72:$0.286H200:$2.663 | GB300 NVL72:$1.193H200:$9.940 |
| Concurrency | GB300 NVL72:~1402H200:~133 | GB300 NVL72:~578H200:~6 | GB300 NVL72:~134H200:~14 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.