MiniMax M3 428B — B300 vs MI325X Performance per Dollar
Cost per million tokens of B300 (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.
At 55 tok/s/user on MiniMax M3 428B, B300 costs $0.34 per million tokens; MI325X costs $0.69. B300 is 106% more cost-efficient at this operating point.
B300 edges MI325X at 97 tok/s/user on MiniMax M3 428B — $1.13 per million tokens versus $1.75, a 55% cost-per-token gap.
Push MiniMax M3 428B to 140 tok/s/user and B300 lands at $2.54 per million tokens against MI325X's $3.13 — B300 pulls ahead by 23%. (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): B300 $2.34/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 | B300:$0.338MI325X:$0.695 | B300:$1.131MI325X:$1.750 | B300:$2.543MI325X:$3.128 |
| Concurrency | B300:~76MI325X:~41 | B300:~29MI325X:~9 | B300:~8MI325X:~3 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.