MiniMax M2.5/M2.7 · Performance per Dollar
MiniMax M2.5/M2.7 — B300 vs MI325X Performance per Dollar
Cost per million tokens of B300 (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.
B300 edges MI325X at 35 tok/s/user on MiniMax M2.5/M2.7 — $0.055 per million tokens versus $0.12, a 53% lower cost per token.
Push MiniMax M2.5/M2.7 to 56 tok/s/user and B300 lands at $0.081 per million tokens against MI325X's $0.17 — B300 costs 52% less.
B300: $0.14 per million tokens. MI325X: $0.30. Both at 78 tok/s/user on MiniMax M2.5/M2.7, with B300 52% cheaper. (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): B300 $2.26/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 | B300$0.055MI325X$0.12 | B300$0.081MI325X$0.17 | B300$0.14MI325X$0.30 |
| Concurrency | B300~521MI325X~18 | B300~335MI325X~8 | B300~6MI325X~5 |
