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. Large-hyperscaler-volume ownership TCO normalized by total 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 18–84 tok/s/user interactivity band — at 34 tok/s/user — B200 runs $0.28 per million tokens on GLM 5/5.1 while H200 runs $0.46. B200 is the cheaper choice by 39%.
On GLM 5/5.1 at 51 tok/s/user, the per-million math comes out to $0.37 for B200 and $0.60 for H200; B200 delivers 61% more total tokens per dollar.
At 68 tok/s/user on GLM 5/5.1, B200 costs $0.46 per million tokens; H200 costs $0.78. B200 delivers 70% more tokens per dollar at this operating point. (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.)
Chip pricing (owning hyperscaler): B200 $1.73/chip/hr · H200 $1.22/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
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) |
|---|---|---|---|
| Dollars per Million Tokens | B200$0.28H200$0.46 | B200$0.37H200$0.60 | B200$0.46H200$0.78 |
| Concurrency | B200~254H200~21 | B200~23H200~10 | B200~15H200~6 |
