DeepSeek R1 — GB300 NVL72 vs MI300X Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus MI300X (AMD CDNA 3) 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.
GB300 NVL72 edges MI300X at 36 tok/s/user on DeepSeek R1 — $0.09 per million tokens versus $1.16, a 1220% cost-per-token gap.
Push DeepSeek R1 to 47 tok/s/user and GB300 NVL72 lands at $0.13 per million tokens against MI300X's $1.66 — GB300 NVL72 pulls ahead by 1163%.
GB300 NVL72: $0.20 per million tokens. MI300X: $2.74. Both at 58 tok/s/user on DeepSeek R1, with GB300 NVL72 1238% cheaper. (Numbers reflect the default 1k/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): GB300 NVL72 $2.65/GPU/hr · MI300X $1.12/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:$0.088MI300X:$1.163 | GB300 NVL72:$0.132MI300X:$1.663 | GB300 NVL72:$0.205MI300X:$2.737 |
| Concurrency | GB300 NVL72:~4285MI300X:~31 | GB300 NVL72:~2166MI300X:~17 | GB300 NVL72:~1562MI300X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.