DeepSeek R1 · Performance per Dollar
DeepSeek R1 — B200 vs MI325X Performance per Dollar
Cost per million tokens of B200 (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 35 tok/s/user, the per-million math comes out to $0.085 for B200 and $0.32 for MI325X; B200 delivers 3.7× the total tokens per dollar.
At 57 tok/s/user on DeepSeek R1, B200 costs $0.16 per million tokens; MI325X costs $0.41. B200 delivers 148% more tokens per dollar at this operating point.
B200 edges MI325X at 78 tok/s/user on DeepSeek R1 — $0.22 per million tokens versus $0.50, a 56% 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): B200 $1.73/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 | B200$0.085MI325X$0.32 | B200$0.16MI325X$0.41 | B200$0.22MI325X$0.50 |
| Concurrency | B200~712MI325X~24 | B200~286MI325X~11 | B200~104MI325X~7 |
