MiniMax M2.5/M2.7 — H100 vs MI355X Performance per Dollar
Cost per million tokens of H100 (NVIDIA Hopper) versus MI355X (AMD CDNA 4) 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.
At 59 tok/s/user on MiniMax M2.5/M2.7, H100 costs $0.58 per million tokens; MI355X costs $0.26. MI355X is 119% more cost-efficient at this operating point.
MI355X edges H100 at 78 tok/s/user on MiniMax M2.5/M2.7 — $0.47 per million tokens versus $0.94, a 100% cost-per-token gap.
Push MiniMax M2.5/M2.7 to 98 tok/s/user and H100 lands at $1.82 per million tokens against MI355X's $0.78 — MI355X pulls ahead by 133%. (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:$0.580MI355X:$0.264 | H100:$0.937MI355X:$0.469 | H100:$1.824MI355X:$0.782 |
| Concurrency | H100:~42MI355X:~52 | H100:~12MI355X:~22 | H100:~8MI355X:~5 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.