DeepSeek V4 Pro 1.6T — B200 vs GB200 NVL72 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus GB200 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.
At 55 tok/s/user on DeepSeek V4 Pro 1.6T, B200 costs $0.14 per million tokens; GB200 NVL72 costs $0.06. GB200 NVL72 is 110% more cost-efficient at this operating point.
GB200 NVL72 edges B200 at 105 tok/s/user on DeepSeek V4 Pro 1.6T — $0.09 per million tokens versus $0.56, a 503% cost-per-token gap.
Push DeepSeek V4 Pro 1.6T to 154 tok/s/user and B200 lands at $0.88 per million tokens against GB200 NVL72's $1.17 — B200 pulls ahead by 33%. (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 · 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:$0.136GB200 NVL72:$0.065 | B200:$0.559GB200 NVL72:$0.093 | B200:$0.879GB200 NVL72:$1.169 |
| Concurrency | B200:~91GB200 NVL72:~16349 | B200:~9GB200 NVL72:~2152 | B200:~4GB200 NVL72:~45 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.