DeepSeek R1 — GB200 NVL72 vs MI355X Performance per Dollar
Cost per million tokens of GB200 NVL72 (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 74 tok/s/user and GB200 NVL72 lands at $0.08 per million tokens against MI355X's $0.22 — GB200 NVL72 pulls ahead by 184%.
GB200 NVL72: $0.38 per million tokens. MI355X: $0.86. Both at 130 tok/s/user on DeepSeek R1, with GB200 NVL72 126% cheaper.
Toward the upper edge of the 18–242 tok/s/user interactivity band — at 186 tok/s/user — GB200 NVL72 runs $0.99 per million tokens on DeepSeek R1 while MI355X runs $2.21. GB200 NVL72 is the cheaper choice by 124%. (Numbers reflect the default 1k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
GPU pricing (owning hyperscaler): GB200 NVL72 $2.21/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 | GB200 NVL72:$0.079MI355X:$0.223 | GB200 NVL72:$0.380MI355X:$0.859 | GB200 NVL72:$0.986MI355X:$2.205 |
| Concurrency | GB200 NVL72:~2211MI355X:~253 | GB200 NVL72:~316MI355X:~58 | GB200 NVL72:~102MI355X:~4 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.