DeepSeek R1 — GB300 NVL72 vs MI355X Performance per Dollar
Cost per million tokens of GB300 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.
On DeepSeek R1 at 95 tok/s/user, the per-million math comes out to $0.06 for GB300 NVL72 and $0.05 for MI355X; MI355X delivers 11% more output per dollar.
At 167 tok/s/user on DeepSeek R1, GB300 NVL72 costs $0.16 per million tokens; MI355X costs $0.22. GB300 NVL72 is 41% more cost-efficient at this operating point.
GB300 NVL72 $0.77 and MI355X $0.76 per million tokens at 240 tok/s/user on DeepSeek R1: effectively the same cost. (Numbers reflect the default 8k/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): GB300 NVL72 $2.65/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 | GB300 NVL72:$0.060MI355X:$0.054 | GB300 NVL72:$0.155MI355X:$0.218 | GB300 NVL72:$0.765MI355X:$0.764 |
| Concurrency | GB300 NVL72:~690MI355X:~204 | GB300 NVL72:~181MI355X:~55 | GB300 NVL72:~23MI355X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.