Kimi K2.5/K2.6 1T — MI325X vs MI355X Performance per Dollar
Cost per million tokens of MI325X (AMD CDNA 3) versus MI355X (AMD CDNA 4) on Kimi K2.5/K2.6 1T. 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 Kimi K2.5/K2.6 1T to 22 tok/s/user and MI325X lands at $2.43 per million tokens against MI355X's $4.04 — MI325X pulls ahead by 66%.
MI325X: $2.60 per million tokens. MI355X: $6.51. Both at 29 tok/s/user on Kimi K2.5/K2.6 1T, with MI325X 151% cheaper.
Toward the upper edge of the 16–43 tok/s/user interactivity band — at 36 tok/s/user — MI325X runs $3.19 per million tokens on Kimi K2.5/K2.6 1T while MI355X runs $8.46. MI325X is the cheaper choice by 166%. (Numbers reflect the default 1k/1k · int4 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:$2.433MI355X:$4.043 | MI325X:$2.597MI355X:$6.513 | MI325X:$3.187MI355X:$8.464 |
| Concurrency | MI325X:~27MI355X:~20 | MI325X:~19MI355X:~9 | MI325X:~13MI355X:~6 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.