DeepSeek V4 Pro 1.6T — B300 vs GB300 NVL72 Performance per Dollar
Cost per million tokens of B300 (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.
Push DeepSeek V4 Pro 1.6T to 54 tok/s/user and B300 lands at $0.35 per million tokens against GB300 NVL72's $0.07 — GB300 NVL72 pulls ahead by 430%.
B300: $0.64 per million tokens. GB300 NVL72: $0.12. Both at 95 tok/s/user on DeepSeek V4 Pro 1.6T, with GB300 NVL72 446% cheaper.
Toward the upper edge of the 13–177 tok/s/user interactivity band — at 136 tok/s/user — B300 runs $1.17 per million tokens on DeepSeek V4 Pro 1.6T while GB300 NVL72 runs $0.24. GB300 NVL72 is the cheaper choice by 389%. (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): B300 $2.34/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 | B300:$0.353GB300 NVL72:$0.067 | B300:$0.640GB300 NVL72:$0.117 | B300:$1.170GB300 NVL72:$0.239 |
| Concurrency | B300:~17GB300 NVL72:~2440 | B300:~5GB300 NVL72:~353 | B300:~2GB300 NVL72:~256 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.