GLM 5.3 744B — B200 vs GB200 NVL72 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus GB200 NVL72 (NVIDIA Blackwell) on GLM 5.3 744B. Owning-hyperscaler 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.
AgentX replays real coding-agent sessions rather than fixed-length prompts, so context grows turn over turn and most of each request is served from cache instead of being recomputed. That turns the comparison into a systems question: KV transfer between nodes, prefix-aware routing, and cache capacity all move the curve alongside raw chip throughput. Fixed-sequence workloads stay the clean baseline for kernel and silicon performance, so the two scenarios answer different questions about the same hardware. Learn more about AgentX →
B200: $0.06 per million tokens. GB200 NVL72: $0.04. Both at 146 tok/s/user on GLM 5.3 744B, with GB200 NVL72 38% cheaper.
Around the middle of the 96–298 tok/s/user interactivity band — at 197 tok/s/user — B200 runs $0.07 per million tokens on GLM 5.3 744B while GB200 NVL72 runs $0.06. GB200 NVL72 is the cheaper choice by 11%.
On GLM 5.3 744B at 248 tok/s/user, the per-million math comes out to $0.11 for B200 and $0.11 for GB200 NVL72; GB200 NVL72 delivers 4% more total tokens per dollar. (Numbers reflect the default agentic-traces · fp4 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 · GB200 NVL72 $1.86/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | B200:$0.058GB200 NVL72:$0.042 | B200:$0.069GB200 NVL72:$0.063 | B200:$0.109GB200 NVL72:$0.105 |
| Concurrency | B200:~12GB200 NVL72:~61 | B200:~8GB200 NVL72:~32 | B200:~5GB200 NVL72:~5 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
No data available
No measurements to plot for this selection. Review the benchmark controls above or adjust quick filters.