DeepSeek R1 · Performance per Dollar

DeepSeek R1 — B200 vs GB300 NVL72 Performance per Dollar

Cost per million tokens of B200 (NVIDIA Blackwell) versus GB300 NVL72 (NVIDIA Blackwell) on DeepSeek R1. Large-hyperscaler-volume ownership TCO normalized by total 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.

At 92 tok/s/user on DeepSeek R1, B200 costs $0.067 per million tokens; GB300 NVL72 costs $0.051. GB300 NVL72 delivers 32% more tokens per dollar at this operating point.

GB300 NVL72 edges B200 at 161 tok/s/user on DeepSeek R1 — $0.12 per million tokens versus $0.24, a 51% lower cost per token.

Push DeepSeek R1 to 231 tok/s/user and B200 lands at $0.38 per million tokens against GB300 NVL72's $0.60 — B200 costs 37% less. (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.)

Chip pricing (owning hyperscaler): B200 $1.73/chip/hr · GB300 NVL72 $2.31/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.

View full latency and 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)
Dollars per Million Tokens
B200$0.067GB300 NVL72$0.051
B200$0.24GB300 NVL72$0.12
B200$0.38GB300 NVL72$0.60
Concurrency
B200~369GB300 NVL72~727
B200~58GB300 NVL72~224
B200~29GB300 NVL72~26
DeepSeek R1: B200 versus GB300 NVL72 cost per million tokens at matched interactivity levels
B200 versus GB300 NVL72 cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗