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. Owning-hyperscaler TCO normalized by output 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 98 tok/s/user on gpt-oss 120B, GB200 NVL72 costs $0.02 per million tokens; H200 costs $0.11. GB200 NVL72 is 517% more cost-efficient at this operating point.

GB200 NVL72 edges H200 at 156 tok/s/user on gpt-oss 120B — $0.03 per million tokens versus $0.24, a 577% cost-per-token gap.

Push gpt-oss 120B to 215 tok/s/user and GB200 NVL72 lands at $0.07 per million tokens against H200's $0.49 — GB200 NVL72 pulls ahead by 600%. (Numbers reflect the default 1k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)

GPU pricing (owning hyperscaler): GB200 NVL72 $2.21/GPU/hr · H200 $1.41/GPU/hr. Source: SemiAnalysis Market August 2025 Pricing Surveys & AI Cloud TCO Model.

View full latency + 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)
Dollar per Million Tokens
GB200 NVL72:$0.019H200:$0.114
GB200 NVL72:$0.035H200:$0.236
GB200 NVL72:$0.070H200:$0.488
Concurrency
GB200 NVL72:~656H200:~64
GB200 NVL72:~3067H200:~42
GB200 NVL72:~103H200:~15

Inference Performance

Inference performance metrics across different models, hardware configurations, and serving parameters.