gpt-oss 120B — B200 vs Jalapeño Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) 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.
On gpt-oss 120B at 177 tok/s/user, the per-million math comes out to $0.02 for B200 and $0.01 for Jalapeño; Jalapeño delivers 279% more total tokens per dollar.
At 258 tok/s/user on gpt-oss 120B, B200 costs $0.04 per million tokens; Jalapeño costs $0.01. Jalapeño is 420% more cost-efficient at this operating point.
Jalapeño edges B200 at 338 tok/s/user on gpt-oss 120B — $0.01 per million tokens versus $0.08, a 738% 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): B200 $1.73/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 | B200:$0.024Jalapeño:$0.006 | B200:$0.039Jalapeño:$0.007 | B200:$0.084Jalapeño:$0.010 |
| Concurrency | B200:~28Jalapeño:~820 | B200:~5Jalapeño:~397 | B200:~8Jalapeño:~181 |