MiniMax M2.5/M2.7 — B300 vs MI355X Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) 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.
Near the low end of the 16–117 tok/s/user interactivity band — at 41 tok/s/user — B300 runs $0.10 per million tokens on MiniMax M2.5/M2.7 while MI355X runs $0.11. B300 is the cheaper choice by 5%.
On MiniMax M2.5/M2.7 at 67 tok/s/user, the per-million math comes out to $0.25 for B300 and $0.35 for MI355X; B300 delivers 43% more output per dollar.
At 92 tok/s/user on MiniMax M2.5/M2.7, B300 costs $0.54 per million tokens; MI355X costs $0.71. B300 is 31% more cost-efficient at this operating point. (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.)
GPU pricing (owning hyperscaler): B300 $2.34/GPU/hr · MI355X $1.48/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 | B300:$0.105MI355X:$0.110 | B300:$0.246MI355X:$0.351 | B300:$0.544MI355X:$0.714 |
| Concurrency | B300:~339MI355X:~256 | B300:~80MI355X:~37 | B300:~26MI355X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.