MiniMax M2.5/M2.7 — GB200 NVL72 vs MI355X Performance per Dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) 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.
On MiniMax M2.5/M2.7 at 42 tok/s/user, the per-million math comes out to $0.10 for GB200 NVL72 and $0.11 for MI355X; GB200 NVL72 delivers 9% more output per dollar.
At 68 tok/s/user on MiniMax M2.5/M2.7, GB200 NVL72 costs $0.24 per million tokens; MI355X costs $0.36. GB200 NVL72 is 48% more cost-efficient at this operating point.
MI355X edges GB200 NVL72 at 93 tok/s/user on MiniMax M2.5/M2.7 — $0.70 per million tokens versus $0.79, a 13% 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): GB200 NVL72 $2.21/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 | GB200 NVL72:$0.102MI355X:$0.111 | GB200 NVL72:$0.240MI355X:$0.357 | GB200 NVL72:$0.794MI355X:$0.703 |
| Concurrency | GB200 NVL72:~1024MI355X:~256 | GB200 NVL72:~209MI355X:~17 | GB200 NVL72:~32MI355X:~6 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.