DeepSeek R1 — GB200 NVL72 vs GB300 NVL72 Performance per Dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus GB300 NVL72 (NVIDIA Blackwell) 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 85 tok/s/user on DeepSeek R1, GB200 NVL72 costs $0.08 per million tokens; GB300 NVL72 costs $0.07. GB300 NVL72 is 13% more cost-efficient at this operating point.
GB300 NVL72 edges GB200 NVL72 at 152 tok/s/user on DeepSeek R1 — $0.28 per million tokens versus $0.45, a 61% cost-per-token gap.
Push DeepSeek R1 to 219 tok/s/user and GB200 NVL72 lands at $2.11 per million tokens against GB300 NVL72's $2.62 — GB200 NVL72 pulls ahead by 24%. (Numbers reflect the default 1k/1k · fp4 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 · GB300 NVL72 $2.65/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:$0.079GB300 NVL72:$0.070 | GB200 NVL72:$0.447GB300 NVL72:$0.277 | GB200 NVL72:$2.110GB300 NVL72:$2.617 |
| Concurrency | GB200 NVL72:~2246GB300 NVL72:~1780 | GB200 NVL72:~226GB300 NVL72:~406 | GB200 NVL72:~27GB300 NVL72:~24 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.