GLM 5/5.1 — B200 vs H200 Performance per Dollar
Cost per million tokens of B200 (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.
Near the low end of the 21–101 tok/s/user interactivity band — at 41 tok/s/user — B200 runs $1.16 per million tokens on GLM 5/5.1 while H200 runs $1.19. B200 is the cheaper choice by 3%.
On GLM 5/5.1 at 61 tok/s/user, the per-million math comes out to $1.39 for B200 and $1.85 for H200; B200 delivers 33% more output per dollar.
At 82 tok/s/user on GLM 5/5.1, B200 costs $1.97 per million tokens; H200 costs $2.93. B200 is 49% more cost-efficient at this operating point. (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 · 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 | B200:$1.159H200:$1.190 | B200:$1.391H200:$1.847 | B200:$1.972H200:$2.933 |
| Concurrency | B200:~484H200:~34 | B200:~25H200:~14 | B200:~14H200:~7 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.