MiniMax M3 428B — H200 vs MI325X Performance per Dollar
Cost per million tokens of H200 (NVIDIA Hopper) 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.
On MiniMax M3 428B at 51 tok/s/user, the per-million math comes out to $0.38 for H200 and $0.62 for MI325X; H200 delivers 62% more output per dollar.
At 95 tok/s/user on MiniMax M3 428B, H200 costs $0.69 per million tokens; MI325X costs $1.70. H200 is 147% more cost-efficient at this operating point.
H200 edges MI325X at 138 tok/s/user on MiniMax M3 428B — $1.06 per million tokens versus $3.06, a 188% cost-per-token gap. (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): H200 $1.41/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 | H200:$0.384MI325X:$0.623 | H200:$0.687MI325X:$1.697 | H200:$1.062MI325X:$3.056 |
| Concurrency | H200:~44MI325X:~49 | H200:~13MI325X:~9 | H200:~5MI325X:~4 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.