MiniMax M2.5/M2.7 — H100 vs MI325X Performance per Dollar
Cost per million tokens of H100 (NVIDIA Hopper) versus MI325X (AMD CDNA 3) on MiniMax M2.5/M2.7. 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.
H100: $0.52 per million tokens. MI325X: $0.28. Both at 56 tok/s/user on MiniMax M2.5/M2.7, with MI325X 85% cheaper.
Around the middle of the 40–105 tok/s/user interactivity band — at 72 tok/s/user — H100 runs $0.82 per million tokens on MiniMax M2.5/M2.7 while MI325X runs $0.49. MI325X is the cheaper choice by 67%.
On MiniMax M2.5/M2.7 at 89 tok/s/user, the per-million math comes out to $1.34 for H100 and $1.27 for MI325X; MI325X delivers 5% more output per dollar. (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): H100 $1.30/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 | H100:$0.517MI325X:$0.279 | H100:$0.820MI325X:$0.491 | H100:$1.340MI325X:$1.270 |
| Concurrency | H100:~50MI325X:~94 | H100:~20MI325X:~40 | H100:~8MI325X:~13 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.