Kimi K2.5/K2.6/K2.7-Code 1T — GB200 NVL72 vs Jalapeño Performance per Dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus Jalapeño (OpenAI Jalapeño) 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.
On Kimi K2.5/K2.6/K2.7-Code 1T at 90 tok/s/user, the per-million math comes out to $0.27 for GB200 NVL72 and $0.03 for Jalapeño; Jalapeño delivers 782% more total tokens per dollar.
At 120 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, GB200 NVL72 costs $0.40 per million tokens; Jalapeño costs $0.04. Jalapeño is 1018% more cost-efficient at this operating point.
Jalapeño edges GB200 NVL72 at 150 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T — $0.04 per million tokens versus $0.93, a 1963% cost-per-token gap. (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): GB200 NVL72 $1.86/chip/hr · Jalapeño $1.27/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 | GB200 NVL72:$0.271Jalapeño:$0.031 | GB200 NVL72:$0.402Jalapeño:$0.036 | GB200 NVL72:$0.926Jalapeño:$0.045 |
| Concurrency | GB200 NVL72:~151Jalapeño:~1087 | GB200 NVL72:~39Jalapeño:~595 | GB200 NVL72:~23Jalapeño:~324 |