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 47 tok/s/user on GLM 5/5.1, B300 costs $0.33 per million tokens; GB300 NVL72 costs $0.61. B300 is 89% more cost-efficient at this operating point.
B300 edges GB300 NVL72 at 61 tok/s/user on GLM 5/5.1 — $0.42 per million tokens versus $1.93, a 361% cost-per-token gap.
Push GLM 5/5.1 to 75 tok/s/user and B300 lands at $0.56 per million tokens against GB300 NVL72's $5.45 — B300 pulls ahead by 867%. (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:$0.326GB300 NVL72:$0.614 | B300:$0.419GB300 NVL72:$1.931 | B300:$0.564GB300 NVL72:$5.452 |
| Concurrency | B300:~85GB300 NVL72:~513 | B300:~52GB300 NVL72:~258 | B300:~32GB300 NVL72:~70 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.