DeepSeek R1 · Performance per Dollar

DeepSeek R1 — B300 vs H200 Performance per Dollar

Cost per million tokens of B300 (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.

Push DeepSeek R1 to 51 tok/s/user and B300 lands at $0.11 per million tokens against H200's $0.23 — B300 costs 52% less.

B300: $0.28 per million tokens. H200: $0.43. Both at 90 tok/s/user on DeepSeek R1, with B300 35% cheaper.

Toward the upper edge of the 13–167 tok/s/user interactivity band — at 129 tok/s/user — B300 runs $0.58 per million tokens on DeepSeek R1 while H200 runs $0.65. B300 is the cheaper choice by 10%. (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): B300 $2.26/chip/hr · H200 $1.22/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
B300$0.11H200$0.23
B300$0.28H200$0.43
B300$0.58H200$0.65
Concurrency
B300~277H200~54
B300~55H200~8
B300~8H200~4
DeepSeek R1: B300 versus H200 cost per million tokens at matched interactivity levels
B300 versus H200 cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗