GLM 5/5.1 — B300 vs H200 Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus H200 (NVIDIA Hopper) 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: $0.79 per million tokens. H200: $1.19. Both at 41 tok/s/user on GLM 5/5.1, with B300 50% cheaper.
Around the middle of the 21–101 tok/s/user interactivity band — at 61 tok/s/user — B300 runs $1.12 per million tokens on GLM 5/5.1 while H200 runs $1.85. B300 is the cheaper choice by 65%.
On GLM 5/5.1 at 82 tok/s/user, the per-million math comes out to $1.57 for B300 and $2.93 for H200; B300 delivers 87% 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): B300 $2.34/GPU/hr · H200 $1.41/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:$0.791H200:$1.190 | B300:$1.119H200:$1.847 | B300:$1.569H200:$2.933 |
| Concurrency | B300:~82H200:~34 | B300:~39H200:~14 | B300:~21H200:~7 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.