GLM 5/5.1 — B300 vs GB300 NVL72 Performance per Dollar
Cost per million tokens of B300 (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.
At 61 tok/s/user on GLM 5/5.1, B300 costs $0.41 per million tokens; GB300 NVL72 costs $0.09. GB300 NVL72 is 334% more cost-efficient at this operating point.
GB300 NVL72 edges B300 at 98 tok/s/user on GLM 5/5.1 — $0.27 per million tokens versus $0.94, a 252% cost-per-token gap.
Push GLM 5/5.1 to 136 tok/s/user and B300 lands at $1.73 per million tokens against GB300 NVL72's $2.98 — B300 pulls ahead by 72%. (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): B300 $2.34/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 | B300:$0.406GB300 NVL72:$0.094 | B300:$0.937GB300 NVL72:$0.266 | B300:$1.733GB300 NVL72:$2.978 |
| Concurrency | B300:~54GB300 NVL72:~1581 | B300:~14GB300 NVL72:~472 | B300:~5GB300 NVL72:~49 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.