gpt-oss 120B — H200 vs Jalapeño Performance per Dollar
Cost per million tokens of H200 (NVIDIA Hopper) versus Jalapeño (OpenAI Jalapeño) on gpt-oss 120B. 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 H200 at 137 tok/s/user on gpt-oss 120B — $0.01 per million tokens versus $0.07, a 1043% cost-per-token gap.
Push gpt-oss 120B to 176 tok/s/user and H200 lands at $0.09 per million tokens against Jalapeño's $0.01 — Jalapeño pulls ahead by 1362%.
H200: $0.15 per million tokens. Jalapeño: $0.01. Both at 216 tok/s/user on gpt-oss 120B, with Jalapeño 2052% 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): H200 $1.22/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 | H200:$0.070Jalapeño:$0.006 | H200:$0.094Jalapeño:$0.006 | H200:$0.147Jalapeño:$0.007 |
| Concurrency | H200:~16Jalapeño:~1316 | H200:~10Jalapeño:~828 | H200:~5Jalapeño:~588 |