DeepSeek R1 — B200 vs MI355X Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) 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 60 tok/s/user and B200 lands at $0.19 per million tokens against MI355X's $0.22 — B200 pulls ahead by 16%.
B200: $0.42 per million tokens. MI355X: $0.40. Both at 108 tok/s/user on DeepSeek R1, with MI355X 6% cheaper.
Toward the upper edge of the 12–204 tok/s/user interactivity band — at 156 tok/s/user — B200 runs $0.72 per million tokens on DeepSeek R1 while MI355X runs $0.55. MI355X is the cheaper choice by 31%. (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): B200 $1.95/GPU/hr · MI355X $1.48/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 | B200:$0.186MI355X:$0.216 | B200:$0.422MI355X:$0.399 | B200:$0.717MI355X:$0.545 |
| Concurrency | B200:~280MI355X:~35 | B200:~71MI355X:~27 | B200:~60MI355X:~4 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.