DeepSeek V4 Pro 1.6T — GB200 NVL72 vs GB300 NVL72 Performance per Dollar
Cost per million tokens of GB200 NVL72 (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.
GB200 NVL72 edges GB300 NVL72 at 62 tok/s/user on DeepSeek V4 Pro 1.6T — $0.07 per million tokens versus $0.07, a 12% cost-per-token gap.
Push DeepSeek V4 Pro 1.6T to 109 tok/s/user and GB200 NVL72 lands at $0.10 per million tokens against GB300 NVL72's $0.12 — GB200 NVL72 pulls ahead by 22%.
GB200 NVL72: $1.18 per million tokens. GB300 NVL72: $0.76. Both at 157 tok/s/user on DeepSeek V4 Pro 1.6T, with GB300 NVL72 54% cheaper. (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): 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:$0.066GB300 NVL72:$0.074 | GB200 NVL72:$0.098GB300 NVL72:$0.119 | GB200 NVL72:$1.176GB300 NVL72:$0.764 |
| Concurrency | GB200 NVL72:~12312GB300 NVL72:~1043 | GB200 NVL72:~1934GB300 NVL72:~613 | GB200 NVL72:~41GB300 NVL72:~31 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.