DeepSeek R1 · Performance per Dollar
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. Large-hyperscaler-volume ownership TCO normalized by total 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 $0.052 for GB300 NVL72 and $0.055 for MI355X; GB300 NVL72 delivers 6% more total tokens per dollar.
At 167 tok/s/user on DeepSeek R1, GB300 NVL72 costs $0.14 per million tokens; MI355X costs $0.22. GB300 NVL72 delivers 61% more tokens per dollar at this operating point.
GB300 NVL72 edges MI355X at 240 tok/s/user on DeepSeek R1 — $0.67 per million tokens versus $0.77, a 13% lower cost per token. (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.)
Chip pricing (owning hyperscaler): GB300 NVL72 $2.31/chip/hr · MI355X $1.50/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollars per Million Tokens | GB300 NVL72$0.052MI355X$0.055 | GB300 NVL72$0.14MI355X$0.22 | GB300 NVL72$0.67MI355X$0.77 |
| Concurrency | GB300 NVL72~690MI355X~204 | GB300 NVL72~181MI355X~55 | GB300 NVL72~23MI355X~8 |
