DeepSeek R1 · Performance per Dollar
DeepSeek R1 — GB200 NVL72 vs MI325X Performance per Dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus MI325X (AMD CDNA 3) 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 49 tok/s/user, the per-million math comes out to $0.079 for GB200 NVL72 and $0.38 for MI325X; GB200 NVL72 delivers 4.8× the total tokens per dollar.
At 66 tok/s/user on DeepSeek R1, GB200 NVL72 costs $0.086 per million tokens; MI325X costs $0.44. GB200 NVL72 delivers 5.2× the tokens per dollar at this operating point.
GB200 NVL72 edges MI325X at 83 tok/s/user on DeepSeek R1 — $0.095 per million tokens versus $0.54, a 82% lower cost per token. (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.)
Chip pricing (owning hyperscaler): GB200 NVL72 $1.86/chip/hr · MI325X $1.10/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 | GB200 NVL72$0.079MI325X$0.38 | GB200 NVL72$0.086MI325X$0.44 | GB200 NVL72$0.095MI325X$0.54 |
| Concurrency | GB200 NVL72~1,994MI325X~15 | GB200 NVL72~939MI325X~9 | GB200 NVL72~437MI325X~6 |
