Kimi K2.5/K2.6/K2.7-Code 1T · Performance per Dollar
Kimi K2.5/K2.6/K2.7-Code 1T — B300 vs MI300X Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus MI300X (AMD CDNA 3) 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 28 tok/s/user and B300 lands at $0.20 per million tokens against MI300X's $0.83 — B300 costs 76% less.
B300: $0.24 per million tokens. MI300X: $1.03. Both at 33 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, with B300 77% cheaper.
Toward the upper edge of the 23–43 tok/s/user interactivity band — at 38 tok/s/user — B300 runs $0.28 per million tokens on Kimi K2.5/K2.6/K2.7-Code 1T while MI300X runs $1.22. B300 is the cheaper choice by 77%. (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): B300 $2.26/chip/hr · MI300X $0.95/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 | B300$0.20MI300X$0.83 | B300$0.24MI300X$1.03 | B300$0.28MI300X$1.22 |
| Concurrency | B300~48MI300X~11 | B300~35MI300X~7 | B300~26MI300X~5 |
