DeepSeek R1 — B300 vs Jalapeño Performance per Dollar
Cost per million tokens of B300 (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.
Jalapeño edges B300 at 129 tok/s/user on DeepSeek R1 — $0.03 per million tokens versus $0.20, a 519% cost-per-token gap.
Push DeepSeek R1 to 192 tok/s/user and B300 lands at $0.45 per million tokens against Jalapeño's $0.05 — Jalapeño pulls ahead by 764%.
B300: $0.76 per million tokens. Jalapeño: $0.17. Both at 255 tok/s/user on DeepSeek R1, with Jalapeño 359% cheaper. (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): B300 $2.26/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 | B300:$0.200Jalapeño:$0.032 | B300:$0.448Jalapeño:$0.052 | B300:$0.764Jalapeño:$0.166 |
| Concurrency | B300:~64Jalapeño:~632 | B300:~40Jalapeño:~203 | B300:~27Jalapeño:~37 |