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 31 tok/s/user on GLM 5/5.1, B300 costs $0.63 per million tokens; GB300 NVL72 costs $0.19. GB300 NVL72 is 226% more cost-efficient at this operating point.
B300 edges GB300 NVL72 at 43 tok/s/user on GLM 5/5.1 — $0.83 per million tokens versus $2.67, a 223% cost-per-token gap.
Push GLM 5/5.1 to 55 tok/s/user and B300 lands at $1.02 per million tokens against GB300 NVL72's $7.90 — B300 pulls ahead by 673%. (Numbers reflect the default 1k/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): 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:$0.627GB300 NVL72:$0.193 | B300:$0.826GB300 NVL72:$2.674 | B300:$1.023GB300 NVL72:$7.904 |
| Concurrency | B300:~140GB300 NVL72:~6137 | B300:~76GB300 NVL72:~258 | B300:~46GB300 NVL72:~67 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.