MiniMax M3 428B — H100 vs MI355X Performance per Dollar
Cost per million tokens of H100 (NVIDIA Hopper) versus MI355X (AMD CDNA 4) 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.
H100: $0.35 per million tokens. MI355X: $0.20. Both at 23 tok/s/user on MiniMax M3 428B, with MI355X 79% cheaper.
Around the middle of the 15–46 tok/s/user interactivity band — at 31 tok/s/user — H100 runs $0.35 per million tokens on MiniMax M3 428B while MI355X runs $0.23. MI355X is the cheaper choice by 51%.
On MiniMax M3 428B at 38 tok/s/user, the per-million math comes out to $0.36 for H100 and $0.29 for MI355X; MI355X delivers 24% 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 · MI355X $1.48/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:$0.351MI355X:$0.196 | H100:$0.351MI355X:$0.232 | H100:$0.363MI355X:$0.293 |
| Concurrency | H100:~128MI355X:~196 | H100:~128MI355X:~127 | H100:~117MI355X:~92 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.