MiniMax M2.5/M2.7 · Performance per Dollar

MiniMax M2.5/M2.7 — B200 vs MI300X Performance per Dollar

Cost per million tokens of B200 (NVIDIA Blackwell) versus MI300X (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.

B200: $0.039 per million tokens. MI300X: $0.17. Both at 31 tok/s/user on MiniMax M2.5/M2.7, with B200 77% cheaper.

Around the middle of the 14–84 tok/s/user interactivity band — at 49 tok/s/user — B200 runs $0.058 per million tokens on MiniMax M2.5/M2.7 while MI300X runs $0.19. B200 is the cheaper choice by 70%.

On MiniMax M2.5/M2.7 at 67 tok/s/user, the per-million math comes out to $0.10 for B200 and $0.25 for MI300X; B200 delivers 140% more total tokens per dollar. (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 · MI300X $0.95/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.

View full latency and throughput comparison →

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$0.039MI300X$0.17
B200$0.058MI300X$0.19
B200$0.10MI300X$0.25
Concurrency
B200~1,019MI300X~18
B200~128MI300X~6
B200~16MI300X~4
MiniMax M2.5/M2.7: B200 versus MI300X cost per million tokens at matched interactivity levels
B200 versus MI300X cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗