GLM 5.3 744B — B200 vs GB300 NVL72 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus GB300 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 →
Near the low end of the 96–297 tok/s/user interactivity band — at 146 tok/s/user — B200 runs $0.06 per million tokens on GLM 5.3 744B while GB300 NVL72 runs $0.05. GB300 NVL72 is the cheaper choice by 26%.
On GLM 5.3 744B at 197 tok/s/user, the per-million math comes out to $0.07 for B200 and $0.07 for GB300 NVL72; B200 delivers 3% more total tokens per dollar.
At 247 tok/s/user on GLM 5.3 744B, B200 costs $0.11 per million tokens; GB300 NVL72 costs $0.10. GB300 NVL72 is 3% more cost-efficient at this operating point. (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 · GB300 NVL72 $2.31/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:$0.058GB300 NVL72:$0.046 | B200:$0.069GB300 NVL72:$0.072 | B200:$0.108GB300 NVL72:$0.104 |
| Concurrency | B200:~12GB300 NVL72:~58 | B200:~8GB300 NVL72:~23 | B200:~5GB300 NVL72:~15 |
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.