DeepSeek R1 · Performance per Dollar
DeepSeek R1 — B300 vs MI300X Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus MI300X (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 23 tok/s/user, the per-million math comes out to $0.087 for B300 and $0.37 for MI300X; B300 delivers 4.3× the total tokens per dollar.
At 33 tok/s/user on DeepSeek R1, B300 costs $0.094 per million tokens; MI300X costs $0.45. B300 delivers 4.8× the tokens per dollar at this operating point.
B300 edges MI300X at 44 tok/s/user on DeepSeek R1 — $0.10 per million tokens versus $0.65, a 84% 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): B300 $2.26/chip/hr · MI300X $0.95/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 | B300$0.087MI300X$0.37 | B300$0.094MI300X$0.45 | B300$0.10MI300X$0.65 |
| Concurrency | B300~1,574MI300X~28 | B300~703MI300X~17 | B300~374MI300X~9 |
