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. 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.
B200: $0.04 per million tokens. MI300X: $0.20. Both at 31 tok/s/user on MiniMax M2.5/M2.7, with B200 347% cheaper.
Around the middle of the 14–84 tok/s/user interactivity band — at 49 tok/s/user — B200 runs $0.06 per million tokens on MiniMax M2.5/M2.7 while MI300X runs $0.22. B200 is the cheaper choice by 244%.
On MiniMax M2.5/M2.7 at 67 tok/s/user, the per-million math comes out to $0.12 for B200 and $0.29 for MI300X; B200 delivers 153% more output 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.)
GPU pricing (owning hyperscaler): B200 $1.95/GPU/hr · MI300X $1.12/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:$0.044MI300X:$0.199 | B200:$0.065MI300X:$0.223 | B200:$0.116MI300X:$0.293 |
| Concurrency | B200:~1019MI300X:~18 | B200:~128MI300X:~6 | B200:~16MI300X:~4 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.