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.
GB300 NVL72 edges GB200 NVL72 at 48 tok/s/user on DeepSeek V4 Pro 1.6T — $0.09 per million tokens versus $0.31, a 233% cost-per-token gap.
Push DeepSeek V4 Pro 1.6T to 83 tok/s/user and GB200 NVL72 lands at $1.40 per million tokens against GB300 NVL72's $0.26 — GB300 NVL72 pulls ahead by 442%.
GB200 NVL72: $3.43 per million tokens. GB300 NVL72: $0.64. Both at 118 tok/s/user on DeepSeek V4 Pro 1.6T, with GB300 NVL72 439% 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:$0.314GB300 NVL72:$0.094 | GB200 NVL72:$1.401GB300 NVL72:$0.258 | GB200 NVL72:$3.428GB300 NVL72:$0.636 |
| Concurrency | GB200 NVL72:~111GB300 NVL72:~1171 | GB200 NVL72:~29GB300 NVL72:~256 | GB200 NVL72:~7GB300 NVL72:~58 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.