MiniMax M2.5/M2.7 · Performance per Dollar
MiniMax M2.5/M2.7 — B200 vs MI325X Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus MI325X (AMD CDNA 3) on MiniMax M2.5/M2.7. Large-hyperscaler-volume ownership TCO normalized by total 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.
Push MiniMax M2.5/M2.7 to 35 tok/s/user and B200 lands at $0.044 per million tokens against MI325X's $0.12 — B200 costs 62% less.
B200: $0.076 per million tokens. MI325X: $0.17. Both at 56 tok/s/user on MiniMax M2.5/M2.7, with B200 55% cheaper.
Toward the upper edge of the 14–99 tok/s/user interactivity band — at 78 tok/s/user — B200 runs $0.15 per million tokens on MiniMax M2.5/M2.7 while MI325X runs $0.30. B200 is the cheaper choice by 52%. (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.)
Chip pricing (owning hyperscaler): B200 $1.73/chip/hr · MI325X $1.10/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollars per Million Tokens | B200$0.044MI325X$0.12 | B200$0.076MI325X$0.17 | B200$0.15MI325X$0.30 |
| Concurrency | B200~823MI325X~18 | B200~90MI325X~8 | B200~32MI325X~5 |
