GLM 5/5.1 — GB200 NVL72 vs H200 Performance per Dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus H200 (NVIDIA Hopper) on GLM 5/5.1. 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 37 tok/s/user on GLM 5/5.1, GB200 NVL72 costs $0.31 per million tokens; H200 costs $0.56. GB200 NVL72 is 79% more cost-efficient at this operating point.
H200 edges GB200 NVL72 at 45 tok/s/user on GLM 5/5.1 — $0.63 per million tokens versus $0.96, a 51% cost-per-token gap.
Push GLM 5/5.1 to 54 tok/s/user and GB200 NVL72 lands at $4.50 per million tokens against H200's $0.73 — H200 pulls ahead by 515%. (Numbers reflect the default 8k/1k · fp8 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.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | GB200 NVL72:$0.311H200:$0.556 | GB200 NVL72:$0.957H200:$0.632 | GB200 NVL72:$4.499H200:$0.731 |
| Concurrency | GB200 NVL72:~931H200:~18 | GB200 NVL72:~150H200:~13 | GB200 NVL72:~27H200:~10 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.