GLM 5/5.1 · Performance per Dollar

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.

B200 $1.19 and H200 $1.19 per million tokens at 41 tok/s/user on GLM 5/5.1: effectively the same cost.

On GLM 5/5.1 at 61 tok/s/user, the per-million math comes out to $1.57 for B200 and $1.85 for H200; B200 delivers 18% more output per dollar.

At 82 tok/s/user on GLM 5/5.1, B200 costs $2.62 per million tokens; H200 costs $2.93. B200 is 12% 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.

View full latency + throughput comparison →

Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
Metric
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Dollar per Million Tokens
B200:$1.188H200:$1.190
B200:$1.569H200:$1.847
B200:$2.623H200:$2.933
Concurrency
B200:~473H200:~34
B200:~22H200:~14
B200:~11H200:~7

Inference Performance

Inference performance metrics across different models, hardware configurations, and serving parameters.