MiniMax M3 428B — B200 vs MI325X Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus MI325X (AMD CDNA 3) on MiniMax M3 428B. 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.
On MiniMax M3 428B at 52 tok/s/user, the per-million math comes out to $0.50 for B200 and $0.64 for MI325X; B200 delivers 29% more output per dollar.
At 95 tok/s/user on MiniMax M3 428B, B200 costs $1.44 per million tokens; MI325X costs $1.70. B200 is 18% more cost-efficient at this operating point.
MI325X edges B200 at 139 tok/s/user on MiniMax M3 428B — $3.09 per million tokens versus $4.28, a 38% cost-per-token gap. (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): B200 $1.95/GPU/hr · MI325X $1.28/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 | B200:$0.496MI325X:$0.640 | B200:$1.438MI325X:$1.697 | B200:$4.278MI325X:$3.092 |
| Concurrency | B200:~53MI325X:~47 | B200:~8MI325X:~9 | B200:~4MI325X:~4 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.