GLM 5/5.1 — B200 vs GB300 NVL72 Performance per Dollar
Cost per million tokens of B200 (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 31 tok/s/user, the per-million math comes out to $0.82 for B200 and $0.19 for GB300 NVL72; GB300 NVL72 delivers 325% more output per dollar.
At 43 tok/s/user on GLM 5/5.1, B200 costs $1.23 per million tokens; GB300 NVL72 costs $2.67. B200 is 118% more cost-efficient at this operating point.
B200 edges GB300 NVL72 at 55 tok/s/user on GLM 5/5.1 — $1.42 per million tokens versus $7.90, a 457% cost-per-token gap. (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): B200 $1.95/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 | B200:$0.820GB300 NVL72:$0.193 | B200:$1.225GB300 NVL72:$2.674 | B200:$1.420GB300 NVL72:$7.904 |
| Concurrency | B200:~450GB300 NVL72:~6137 | B200:~393GB300 NVL72:~258 | B200:~28GB300 NVL72:~67 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.