Kimi K2.5/K2.6/K2.7-Code 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/K2.7-Code 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/K2.7-Code 1T to 27 tok/s/user and MI300X lands at $2.75 per million tokens against MI355X's $0.50 — MI355X pulls ahead by 454%.
MI300X: $3.47 per million tokens. MI355X: $0.65. Both at 34 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, with MI355X 430% cheaper.
Toward the upper edge of the 20–48 tok/s/user interactivity band — at 42 tok/s/user — MI300X runs $4.86 per million tokens on Kimi K2.5/K2.6/K2.7-Code 1T while MI355X runs $0.85. MI355X is the cheaper choice by 471%. (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:$2.754MI355X:$0.497 | MI300X:$3.468MI355X:$0.654 | MI300X:$4.863MI355X:$0.852 |
| Concurrency | MI300X:~17MI355X:~62 | MI300X:~11MI355X:~38 | MI300X:~6MI355X:~23 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.