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 72 tok/s/user and B300 lands at $0.27 per million tokens against GB300 NVL72's $0.08 — GB300 NVL72 pulls ahead by 250%.
B300: $0.53 per million tokens. GB300 NVL72: $0.22. Both at 130 tok/s/user on DeepSeek V4 Pro 1.6T, with GB300 NVL72 143% cheaper.
Toward the upper edge of the 15–244 tok/s/user interactivity band — at 187 tok/s/user — B300 runs $1.23 per million tokens on DeepSeek V4 Pro 1.6T while GB300 NVL72 runs $1.44. B300 is the cheaper choice by 17%. (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:$0.275GB300 NVL72:$0.078 | B300:$0.526GB300 NVL72:$0.216 | B300:$1.228GB300 NVL72:$1.436 |
| Concurrency | B300:~21GB300 NVL72:~1163 | B300:~5GB300 NVL72:~288 | B300:~1GB300 NVL72:~13 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.