Kimi K2.5/K2.6/K2.7-Code 1T — Jalapeño vs MI300X Performance per Dollar
Cost per million tokens of Jalapeño (OpenAI Jalapeño) 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.
At 219 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, Jalapeño comes in at $0.16 per million tokens. MI300X hasn't been benchmarked at this operating point.
Only Jalapeño has cost data at 377 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T — $0.49 per million tokens. MI300X is unmeasured at this target.
Jalapeño costs $0.52 per million tokens at 536 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T; we have no MI300X benchmark data at this exact target. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): Jalapeño $1.27/chip/hr · MI300X $0.95/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | Jalapeño:$0.165MI300X:— | Jalapeño:$0.487MI300X:— | Jalapeño:$0.517MI300X:— |
| Concurrency | Jalapeño:~41MI300X:— | Jalapeño:~2MI300X:— | Jalapeño:~1MI300X:— |