MiniMax M2.5/M2.7 — MI300X vs MI355X Performance per Dollar
Cost per million tokens of MI300X (AMD CDNA 3) 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.
Push MiniMax M2.5/M2.7 to 44 tok/s/user and MI300X lands at $0.25 per million tokens against MI355X's $0.11 — MI355X pulls ahead by 121%.
MI300X: $0.40 per million tokens. MI355X: $0.29. Both at 61 tok/s/user on MiniMax M2.5/M2.7, with MI355X 37% cheaper.
Toward the upper edge of the 27–95 tok/s/user interactivity band — at 78 tok/s/user — MI300X runs $0.75 per million tokens on MiniMax M2.5/M2.7 while MI355X runs $0.47. MI355X is the cheaper choice by 59%. (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): MI300X $1.12/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 | MI300X:$0.250MI355X:$0.113 | MI300X:$0.402MI355X:$0.294 | MI300X:$0.747MI355X:$0.469 |
| Concurrency | MI300X:~63MI355X:~256 | MI300X:~26MI355X:~40 | MI300X:~11MI355X:~22 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.