MiniMax M3 428B — MI300X vs MI325X Performance per Dollar
Cost per million tokens of MI300X (AMD CDNA 3) 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.
Push MiniMax M3 428B to 55 tok/s/user and MI300X lands at $0.87 per million tokens against MI325X's $0.69 — MI325X pulls ahead by 25%.
MI300X: $1.85 per million tokens. MI325X: $1.75. Both at 97 tok/s/user on MiniMax M3 428B, with MI325X 6% cheaper.
Toward the upper edge of the 13–182 tok/s/user interactivity band — at 140 tok/s/user — MI300X runs $2.71 per million tokens on MiniMax M3 428B while MI325X runs $3.13. MI300X is the cheaper choice by 15%. (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): MI300X $1.12/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 | MI300X:$0.871MI325X:$0.695 | MI300X:$1.847MI325X:$1.750 | MI300X:$2.709MI325X:$3.128 |
| Concurrency | MI300X:~29MI325X:~41 | MI300X:~7MI325X:~9 | MI300X:~4MI325X:~3 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.