gpt-oss 120B · Performance per Dollar
gpt-oss 120B — GB200 NVL72 vs H100 Performance per Dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus H100 (NVIDIA Hopper) 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.
GB200 NVL72 edges H100 at 113 tok/s/user on gpt-oss 120B — $0.012 per million tokens versus $0.062, a 80% lower cost per token.
Push gpt-oss 120B to 159 tok/s/user and GB200 NVL72 lands at $0.016 per million tokens against H100's $0.089 — GB200 NVL72 costs 82% less.
GB200 NVL72: $0.020 per million tokens. H100: $0.13. Both at 205 tok/s/user on gpt-oss 120B, with GB200 NVL72 85% 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): GB200 NVL72 $1.86/chip/hr · H100 $1.17/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollars per Million Tokens | GB200 NVL72$0.012H100$0.062 | GB200 NVL72$0.016H100$0.089 | GB200 NVL72$0.020H100$0.13 |
| Concurrency | GB200 NVL72~375H100~25 | GB200 NVL72~291H100~11 | GB200 NVL72~87H100~5 |
