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: $0.33 per million tokens. B300: $0.51. Both at 37 tok/s/user on GLM 5/5.1, with B200 54% cheaper.
Around the middle of the 12–113 tok/s/user interactivity band — at 63 tok/s/user — B200 runs $0.48 per million tokens on GLM 5/5.1 while B300 runs $0.69. B200 is the cheaper choice by 43%.
On GLM 5/5.1 at 88 tok/s/user, the per-million math comes out to $0.70 for B200 and $0.95 for B300; B200 delivers 37% more output per dollar. (Numbers reflect the default 8k/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:$0.332B300:$0.512 | B200:$0.482B300:$0.691 | B200:$0.696B300:$0.953 |
| Concurrency | B200:~216B300:~32 | B200:~17B300:~14 | B200:~9B300:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.