GLM 5.3 744B — GB300 NVL72 vs H200 Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus H200 (NVIDIA Hopper) on GLM 5.3 744B. 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.
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 →
GB300 NVL72 costs $0.04 per million tokens at 139 tok/s/user on GLM 5.3 744B; we have no H200 benchmark data at this exact target.
At 192 tok/s/user on GLM 5.3 744B, GB300 NVL72 comes in at $0.07 per million tokens. H200 hasn't been benchmarked at this operating point.
Only GB300 NVL72 has cost data at 245 tok/s/user on GLM 5.3 744B — $0.10 per million tokens. H200 is unmeasured at this target. (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): GB300 NVL72 $2.31/chip/hr · H200 $1.22/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 | GB300 NVL72:$0.043H200:— | GB300 NVL72:$0.068H200:— | GB300 NVL72:$0.105H200:— |
| Concurrency | GB300 NVL72:~53H200:— | GB300 NVL72:~20H200:— | GB300 NVL72:~17H200:— |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.