gpt-oss 120B · Performance per Dollar

gpt-oss 120B — GB200 NVL72 vs H200 Performance per Dollar

Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus H200 (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.

At 115 tok/s/user on gpt-oss 120B, GB200 NVL72 costs $0.012 per million tokens; H200 costs $0.060. GB200 NVL72 delivers 4.9× the tokens per dollar at this operating point.

GB200 NVL72 edges H200 at 162 tok/s/user on gpt-oss 120B — $0.016 per million tokens versus $0.084, a 81% lower cost per token.

Push gpt-oss 120B to 209 tok/s/user and GB200 NVL72 lands at $0.021 per million tokens against H200's $0.13 — GB200 NVL72 costs 85% less. (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 · H200 $1.22/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.

View full latency and throughput comparison →

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$0.012H200$0.060
GB200 NVL72$0.016H200$0.084
GB200 NVL72$0.021H200$0.13
Concurrency
GB200 NVL72~393H200~16
GB200 NVL72~253H200~13
GB200 NVL72~84H200~5
gpt-oss 120B: GB200 NVL72 versus H200 cost per million tokens at matched interactivity levels
GB200 NVL72 versus H200 cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗