MiniMax M2.5/M2.7 — H100 vs MI300X Performance per Dollar
Cost per million tokens of H100 (NVIDIA Hopper) versus MI300X (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.
Push MiniMax M2.5/M2.7 to 53 tok/s/user and H100 lands at $0.46 per million tokens against MI300X's $0.31 — MI300X pulls ahead by 49%.
H100: $0.73 per million tokens. MI300X: $0.50. Both at 67 tok/s/user on MiniMax M2.5/M2.7, with MI300X 47% cheaper.
Toward the upper edge of the 40–95 tok/s/user interactivity band — at 82 tok/s/user — H100 runs $1.04 per million tokens on MiniMax M2.5/M2.7 while MI300X runs $0.88. MI300X is the cheaper choice by 19%. (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 · MI300X $1.12/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:$0.464MI300X:$0.311 | H100:$0.729MI300X:$0.495 | H100:$1.045MI300X:$0.881 |
| Concurrency | H100:~60MI300X:~41 | H100:~30MI300X:~19 | H100:~8MI300X:~9 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.