GLM 5/5.1 — B200 vs GB200 NVL72 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus GB200 NVL72 (NVIDIA Blackwell) 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.
Push GLM 5/5.1 to 58 tok/s/user and B200 lands at $0.21 per million tokens against GB200 NVL72's $0.06 — GB200 NVL72 pulls ahead by 234%.
B200: $0.30 per million tokens. GB200 NVL72: $0.09. Both at 86 tok/s/user on GLM 5/5.1, with GB200 NVL72 227% cheaper.
Toward the upper edge of the 30–142 tok/s/user interactivity band — at 114 tok/s/user — B200 runs $0.39 per million tokens on GLM 5/5.1 while GB200 NVL72 runs $0.31. GB200 NVL72 is the cheaper choice by 27%. (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.)
GPU pricing (owning hyperscaler): B200 $1.95/GPU/hr · GB200 NVL72 $2.21/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 | B200:$0.214GB200 NVL72:$0.064 | B200:$0.303GB200 NVL72:$0.093 | B200:$0.393GB200 NVL72:$0.309 |
| Concurrency | B200:~20GB200 NVL72:~953 | B200:~10GB200 NVL72:~664 | B200:~5GB200 NVL72:~108 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.