GLM 5/5.1 — GB200 NVL72 vs GB300 NVL72 Performance per Dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus GB300 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.
On GLM 5/5.1 at 67 tok/s/user, the per-million math comes out to $0.07 for GB200 NVL72 and $0.07 for GB300 NVL72; GB200 NVL72 delivers 7% more output per dollar.
At 104 tok/s/user on GLM 5/5.1, GB200 NVL72 and GB300 NVL72 land within ~1% on cost per million tokens ($0.17 vs $0.17) — call it a tie at this operating point.
GB300 NVL72 edges GB200 NVL72 at 141 tok/s/user on GLM 5/5.1 — $0.84 per million tokens versus $0.98, a 16% cost-per-token gap. (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): GB200 NVL72 $2.21/GPU/hr · GB300 NVL72 $2.65/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:$0.068GB300 NVL72:$0.072 | GB200 NVL72:$0.168GB300 NVL72:$0.167 | GB200 NVL72:$0.976GB300 NVL72:$0.839 |
| Concurrency | GB200 NVL72:~698GB300 NVL72:~749 | GB200 NVL72:~231GB300 NVL72:~276 | GB200 NVL72:~62GB300 NVL72:~23 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.