Kimi K2.5/K2.6 1T — MI300X vs MI355X Performance per Dollar
Cost per million tokens of MI300X (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.
MI300X: $2.56 per million tokens. MI355X: $3.78. Both at 21 tok/s/user on Kimi K2.5/K2.6 1T, with MI300X 48% cheaper.
Around the middle of the 14–43 tok/s/user interactivity band — at 28 tok/s/user — MI300X runs $2.83 per million tokens on Kimi K2.5/K2.6 1T while MI355X runs $6.14. MI300X is the cheaper choice by 117%.
On Kimi K2.5/K2.6 1T at 36 tok/s/user, the per-million math comes out to $3.75 for MI300X and $8.46 for MI355X; MI300X delivers 126% more output per dollar. (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): 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:$2.557MI355X:$3.778 | MI300X:$2.829MI355X:$6.139 | MI300X:$3.748MI355X:$8.464 |
| Concurrency | MI300X:~23MI355X:~23 | MI300X:~16MI355X:~10 | MI300X:~10MI355X:~6 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.