DeepSeek R1 · Performance per Dollar

DeepSeek R1 — B300 vs GB300 NVL72 Performance per Dollar

Cost per million tokens of B300 (NVIDIA Blackwell) versus GB300 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.

On DeepSeek R1 at 88 tok/s/user, the per-million math comes out to $0.13 for B300 and $0.07 for GB300 NVL72; GB300 NVL72 delivers 85% more output per dollar.

At 162 tok/s/user on DeepSeek R1, B300 costs $1.18 per million tokens; GB300 NVL72 costs $0.38. GB300 NVL72 is 214% more cost-efficient at this operating point.

B300 edges GB300 NVL72 at 235 tok/s/user on DeepSeek R1 — $2.77 per million tokens versus $3.27, a 18% cost-per-token gap. (Numbers reflect the default 1k/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.

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:$0.134GB300 NVL72:$0.073
B300:$1.182GB300 NVL72:$0.377
B300:$2.765GB300 NVL72:$3.275
Concurrency
B300:~386GB300 NVL72:~1716
B300:~73GB300 NVL72:~286
B300:~22GB300 NVL72:~18

Inference Performance

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