MiniMax M2.5/M2.7 — B300 vs MI300X Performance per Dollar
Cost per million tokens of B300 (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.
Push MiniMax M2.5/M2.7 to 44 tok/s/user and B300 lands at $0.11 per million tokens against MI300X's $0.21 — B300 pulls ahead by 95%.
B300: $0.19 per million tokens. MI300X: $0.34. Both at 61 tok/s/user on MiniMax M2.5/M2.7, with B300 83% cheaper.
Toward the upper edge of the 27–95 tok/s/user interactivity band — at 78 tok/s/user — B300 runs $0.40 per million tokens on MiniMax M2.5/M2.7 while MI300X runs $0.64. B300 is the cheaper choice by 60%. (Numbers reflect the default 1k/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 · MI300X $0.95/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | B300:$0.108MI300X:$0.211 | B300:$0.185MI300X:$0.339 | B300:$0.400MI300X:$0.641 |
| Concurrency | B300:~303MI300X:~63 | B300:~232MI300X:~26 | B300:~47MI300X:~11 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.