MiniMax M3 428B — MI300X vs MI355X Performance per Dollar
Cost per million tokens of MI300X (AMD CDNA 3) 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.
On MiniMax M3 428B at 21 tok/s/user, the per-million math comes out to $0.34 for MI300X and $0.19 for MI355X; MI355X delivers 80% more output per dollar.
At 29 tok/s/user on MiniMax M3 428B, MI300X costs $0.41 per million tokens; MI355X costs $0.22. MI355X is 88% more cost-efficient at this operating point.
MI355X edges MI300X at 38 tok/s/user on MiniMax M3 428B — $0.29 per million tokens versus $0.56, a 91% 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): MI300X $1.12/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 | MI300X:$0.342MI355X:$0.190 | MI300X:$0.411MI355X:$0.219 | MI300X:$0.560MI355X:$0.293 |
| Concurrency | MI300X:~196MI355X:~226 | MI300X:~113MI355X:~143 | MI300X:~65MI355X:~92 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.