GLM 5/5.1 — B200 vs B300 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus B300 (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.
B200: $1.16 per million tokens. B300: $0.77. Both at 40 tok/s/user on GLM 5/5.1, with B300 50% cheaper.
Around the middle of the 17–108 tok/s/user interactivity band — at 63 tok/s/user — B200 runs $1.63 per million tokens on GLM 5/5.1 while B300 runs $1.15. B300 is the cheaper choice by 41%.
On GLM 5/5.1 at 86 tok/s/user, the per-million math comes out to $2.93 for B200 and $1.69 for B300; B300 delivers 74% more output per dollar. (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 · B300 $2.34/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:$1.164B300:$0.774 | B200:$1.627B300:$1.154 | B200:$2.932B300:$1.688 |
| Concurrency | B200:~499B300:~85 | B200:~21B300:~37 | B200:~9B300:~19 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.