Kimi K2.5/K2.6/K2.7-Code 1T · Performance per Dollar
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. Large-hyperscaler-volume ownership TCO normalized by total 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 18 tok/s/user and MI300X lands at $0.63 per million tokens against MI355X's $0.18 — MI355X costs 71% less.
MI300X: $0.79 per million tokens. MI355X: $0.23. Both at 27 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, with MI355X 71% cheaper.
Toward the upper edge of the 10–43 tok/s/user interactivity band — at 35 tok/s/user — MI300X runs $1.11 per million tokens on Kimi K2.5/K2.6/K2.7-Code 1T while MI355X runs $0.28. MI355X is the cheaper choice by 75%. (Numbers reflect the default 8k/1k · int4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): MI300X $0.95/chip/hr · MI355X $1.50/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollars per Million Tokens | MI300X$0.63MI355X$0.18 | MI300X$0.79MI355X$0.23 | MI300X$1.11MI355X$0.28 |
| Concurrency | MI300X~21MI355X~56 | MI300X~11MI355X~31 | MI300X~6MI355X~20 |
