DeepSeek R1 · Performance per Dollar

DeepSeek R1 — B300 vs GB200 NVL72 Performance per Dollar

Cost per million tokens of B300 (NVIDIA Blackwell) versus GB200 NVL72 (NVIDIA Blackwell) on DeepSeek R1. 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 R1 to 90 tok/s/user and B300 lands at $0.08 per million tokens against GB200 NVL72's $0.05 — GB200 NVL72 pulls ahead by 45%.

B300: $0.35 per million tokens. GB200 NVL72: $0.14. Both at 160 tok/s/user on DeepSeek R1, with GB200 NVL72 156% cheaper.

B300 $0.60 and GB200 NVL72 $0.60 per million tokens at 230 tok/s/user on DeepSeek R1: effectively the same cost. (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 · GB200 NVL72 $2.21/GPU/hr. Source: SemiAnalysis Market August 2025 Pricing Surveys & AI Cloud TCO Model.

View full latency + throughput comparison →

Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
Metric
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Dollar per Million Tokens
B300:$0.076GB200 NVL72:$0.052
B300:$0.354GB200 NVL72:$0.139
B300:$0.604GB200 NVL72:$0.601
Concurrency
B300:~214GB200 NVL72:~935
B300:~46GB200 NVL72:~194
B300:~34GB200 NVL72:~19

Inference Performance

Inference performance metrics across different models, hardware configurations, and serving parameters.