DeepSeek R1 — H100 vs Jalapeño
Head-to-head AI inference benchmark comparison of H100 (NVIDIA Hopper) and Jalapeño (OpenAI Jalapeño) on DeepSeek R1. Latency, throughput, and cost across LLM workloads. Use the chart controls below to switch sequences, precisions, and metrics — same interactions as the main inference chart.
H100 hits 739 tok/s/chip for $0.44 per million tokens at 45 tok/s/user on DeepSeek R1. No Jalapeño data at this operating point.
H100: 281 tok/s/chip, $1.16 per million tokens at 71 tok/s/user on DeepSeek R1. Jalapeño is unmeasured here.
At 97 tok/s/user on DeepSeek R1, H100 delivers 154 tok/s/chip at $2.11 per million tokens; Jalapeño hasn't been benchmarked at this target. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | H100:739.5Jalapeño:— | H100:280.6Jalapeño:— | H100:154.3Jalapeño:— |
| Cost ($/M tok) | H100:$0.439Jalapeño:— | H100:$1.158Jalapeño:— | H100:$2.106Jalapeño:— |
| tok/s/MW | H100:539778Jalapeño:— | H100:204852Jalapeño:— | H100:112644Jalapeño:— |
| Concurrency | H100:~132Jalapeño:— | H100:~41Jalapeño:— | H100:~17Jalapeño:— |