GLM 5/5.1 — B300 vs GB200 NVL72 Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus GB200 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.
B300: $0.24 per million tokens. GB200 NVL72: $0.05. Both at 59 tok/s/user on GLM 5/5.1, with GB200 NVL72 347% cheaper.
Around the middle of the 30–147 tok/s/user interactivity band — at 88 tok/s/user — B300 runs $0.36 per million tokens on GLM 5/5.1 while GB200 NVL72 runs $0.08. GB200 NVL72 is the cheaper choice by 330%.
On GLM 5/5.1 at 118 tok/s/user, the per-million math comes out to $0.49 for B300 and $0.33 for GB200 NVL72; GB200 NVL72 delivers 50% more output per dollar. (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.)
Chip pricing (owning hyperscaler): B300 $2.26/chip/hr · GB200 NVL72 $1.86/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | B300:$0.242GB200 NVL72:$0.054 | B300:$0.358GB200 NVL72:$0.083 | B300:$0.491GB200 NVL72:$0.328 |
| Concurrency | B300:~20GB200 NVL72:~916 | B300:~9GB200 NVL72:~661 | B300:~5GB200 NVL72:~75 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.