DeepSeek R1 — GB200 NVL72 vs Jalapeño Performance per Dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus Jalapeño (OpenAI Jalapeño) on DeepSeek R1. 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.
Near the low end of the 66–299 tok/s/user interactivity band — at 124 tok/s/user — GB200 NVL72 runs $0.06 per million tokens on DeepSeek R1 while Jalapeño runs $0.03. Jalapeño is the cheaper choice by 83%.
On DeepSeek R1 at 183 tok/s/user, the per-million math comes out to $0.22 for GB200 NVL72 and $0.05 for Jalapeño; Jalapeño delivers 383% more total tokens per dollar.
At 241 tok/s/user on DeepSeek R1, GB200 NVL72 costs $0.61 per million tokens; Jalapeño costs $0.14. Jalapeño is 350% more cost-efficient at this operating point. (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:$0.058Jalapeño:$0.031 | GB200 NVL72:$0.219Jalapeño:$0.045 | GB200 NVL72:$0.609Jalapeño:$0.135 |
| Concurrency | GB200 NVL72:~679Jalapeño:~685 | GB200 NVL72:~80Jalapeño:~255 | GB200 NVL72:~15Jalapeño:~48 |