DeepSeek R1 · Performance per Dollar

DeepSeek R1 — B200 vs H200 Performance per Dollar

Cost per million tokens of B200 (NVIDIA Blackwell) versus H200 (NVIDIA Hopper) 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.

B200 edges H200 at 51 tok/s/user on DeepSeek R1 — $0.10 per million tokens versus $0.23, a 55% lower cost per token.

Push DeepSeek R1 to 90 tok/s/user and B200 lands at $0.33 per million tokens against H200's $0.43 — B200 costs 24% less.

B200: $0.46 per million tokens. H200: $0.65. Both at 129 tok/s/user on DeepSeek R1, with B200 29% cheaper. (Numbers reflect the default 8k/1k · fp8 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 · H200 $1.22/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.

View full latency and throughput comparison →

B200 vs H200: full specs & benchmarks across models →

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$0.10H200$0.23
B200$0.33H200$0.43
B200$0.46H200$0.65
Concurrency
B200~288H200~54
B200~43H200~8
B200~9H200~4
DeepSeek R1: B200 versus H200 cost per million tokens at matched interactivity levels
B200 versus H200 cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗