MiniMax M2.5/M2.7 — MI325X vs MI355X Performance per Dollar
Cost per million tokens of MI325X (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.
MI325X: $0.22 per million tokens. MI355X: $0.12. Both at 46 tok/s/user on MiniMax M2.5/M2.7, with MI355X 88% cheaper.
Around the middle of the 27–104 tok/s/user interactivity band — at 65 tok/s/user — MI325X runs $0.48 per million tokens on MiniMax M2.5/M2.7 while MI355X runs $0.33. MI355X is the cheaper choice by 43%.
On MiniMax M2.5/M2.7 at 85 tok/s/user, the per-million math comes out to $1.09 for MI325X and $0.58 for MI355X; MI355X delivers 88% 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): MI325X $1.28/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 | MI325X:$0.217MI355X:$0.115 | MI325X:$0.479MI355X:$0.334 | MI325X:$1.094MI355X:$0.581 |
| Concurrency | MI325X:~147MI355X:~256 | MI325X:~38MI355X:~24 | MI325X:~16MI355X:~9 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.