MiniMax M3 428B — H200 vs MI300X Performance per Dollar
Cost per million tokens of H200 (NVIDIA Hopper) versus MI300X (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.
At 55 tok/s/user on MiniMax M3 428B, H200 costs $0.42 per million tokens; MI300X costs $0.87. H200 is 106% more cost-efficient at this operating point.
H200 edges MI300X at 98 tok/s/user on MiniMax M3 428B — $0.72 per million tokens versus $1.86, a 160% cost-per-token gap.
Push MiniMax M3 428B to 142 tok/s/user and H200 lands at $1.09 per million tokens against MI300X's $2.87 — H200 pulls ahead by 164%. (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 · 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 | H200:$0.424MI300X:$0.871 | H200:$0.716MI300X:$1.861 | H200:$1.088MI300X:$2.868 |
| Concurrency | H200:~36MI300X:~29 | H200:~12MI300X:~7 | H200:~5MI300X:~3 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.