MiniMax M3 428B — B300 vs MI355X Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) on MiniMax M3 428B. 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.
B300: $0.17 per million tokens. MI355X: $0.19. Both at 21 tok/s/user on MiniMax M3 428B, with B300 10% cheaper.
Around the middle of the 13–46 tok/s/user interactivity band — at 29 tok/s/user — B300 runs $0.18 per million tokens on MiniMax M3 428B while MI355X runs $0.22. B300 is the cheaper choice by 23%.
On MiniMax M3 428B at 38 tok/s/user, the per-million math comes out to $0.21 for B300 and $0.29 for MI355X; B300 delivers 40% more output per dollar. (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:$0.172MI355X:$0.190 | B300:$0.177MI355X:$0.219 | B300:$0.210MI355X:$0.293 |
| Concurrency | B300:~414MI355X:~226 | B300:~288MI355X:~143 | B300:~181MI355X:~92 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.