MiniMax M2.5/M2.7 — B200 vs MI355X Performance per Dollar
Cost per million tokens of B200 (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 37 tok/s/user, the per-million math comes out to $0.05 for B200 and $0.08 for MI355X; B200 delivers 46% more output per dollar.
At 62 tok/s/user on MiniMax M2.5/M2.7, B200 costs $0.10 per million tokens; MI355X costs $0.13. B200 is 28% more cost-efficient at this operating point.
B200 edges MI355X at 86 tok/s/user on MiniMax M2.5/M2.7 — $0.17 per million tokens versus $0.21, a 22% cost-per-token gap. (Numbers reflect the default 8k/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): B200 $1.95/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 | B200:$0.053MI355X:$0.077 | B200:$0.101MI355X:$0.130 | B200:$0.169MI355X:$0.206 |
| Concurrency | B200:~777MI355X:~67 | B200:~62MI355X:~11 | B200:~25MI355X:~5 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.