DeepSeek V4 Pro 1.6T — B200 vs GB300 NVL72 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus GB300 NVL72 (NVIDIA Blackwell) on DeepSeek V4 Pro 1.6T. 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: $0.17 per million tokens. GB300 NVL72: $0.08. Both at 68 tok/s/user on DeepSeek V4 Pro 1.6T, with GB300 NVL72 124% cheaper.
Around the middle of the 15–226 tok/s/user interactivity band — at 121 tok/s/user — B200 runs $0.64 per million tokens on DeepSeek V4 Pro 1.6T while GB300 NVL72 runs $0.20. GB300 NVL72 is the cheaper choice by 227%.
On DeepSeek V4 Pro 1.6T at 173 tok/s/user, the per-million math comes out to $1.18 for B200 and $0.84 for GB300 NVL72; GB300 NVL72 delivers 40% more output per dollar. (Numbers reflect the default 8k/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): B200 $1.95/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 | B200:$0.169GB300 NVL72:$0.075 | B200:$0.640GB300 NVL72:$0.196 | B200:$1.180GB300 NVL72:$0.841 |
| Concurrency | B200:~56GB300 NVL72:~1024 | B200:~7GB300 NVL72:~315 | B200:~3GB300 NVL72:~29 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.