DeepSeek R1 — B300 vs H200 Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus H200 (NVIDIA Hopper) 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 50 tok/s/user and B300 lands at $0.11 per million tokens against H200's $0.24 — B300 pulls ahead by 115%.
B300: $0.26 per million tokens. H200: $0.69. Both at 89 tok/s/user on DeepSeek R1, with B300 165% cheaper.
Toward the upper edge of the 12–167 tok/s/user interactivity band — at 128 tok/s/user — B300 runs $0.75 per million tokens on DeepSeek R1 while H200 runs $1.33. B300 is the cheaper choice by 77%. (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.)
GPU pricing (owning hyperscaler): B300 $2.34/GPU/hr · H200 $1.41/GPU/hr. Source: SemiAnalysis Market August 2025 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | B300:$0.112H200:$0.241 | B300:$0.260H200:$0.689 | B300:$0.750H200:$1.329 |
| Concurrency | B300:~288H200:~74 | B300:~58H200:~6 | B300:~9H200:~21 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.