DeepSeek R1 — B200 vs GB200 NVL72 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus GB200 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.
B200: $0.23 per million tokens. GB200 NVL72: $0.11. Both at 75 tok/s/user on DeepSeek R1, with GB200 NVL72 113% cheaper.
Around the middle of the 31–208 tok/s/user interactivity band — at 120 tok/s/user — B200 runs $0.49 per million tokens on DeepSeek R1 while GB200 NVL72 runs $0.15. GB200 NVL72 is the cheaper choice by 217%.
On DeepSeek R1 at 164 tok/s/user, the per-million math comes out to $0.72 for B200 and $0.81 for GB200 NVL72; B200 delivers 12% more output per dollar. (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.)
GPU pricing (owning hyperscaler): B200 $1.95/GPU/hr · GB200 NVL72 $2.21/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 | B200:$0.226GB200 NVL72:$0.106 | B200:$0.488GB200 NVL72:$0.154 | B200:$0.721GB200 NVL72:$0.809 |
| Concurrency | B200:~160GB200 NVL72:~649 | B200:~119GB200 NVL72:~333 | B200:~21GB200 NVL72:~27 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.