GLM 5.3 744B — B300 vs GB300 NVL72 Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus GB300 NVL72 (NVIDIA Blackwell) 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 edges B300 at 168 tok/s/user on GLM 5.3 744B — $0.06 per million tokens versus $0.08, a 35% cost-per-token gap.
Push GLM 5.3 744B to 211 tok/s/user and B300 lands at $0.12 per million tokens against GB300 NVL72's $0.07 — GB300 NVL72 pulls ahead by 59%.
B300: $0.15 per million tokens. GB300 NVL72: $0.12. Both at 255 tok/s/user on GLM 5.3 744B, with GB300 NVL72 22% cheaper. (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): B300 $2.26/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 | B300:$0.083GB300 NVL72:$0.062 | B300:$0.117GB300 NVL72:$0.074 | B300:$0.149GB300 NVL72:$0.122 |
| Concurrency | B300:~10GB300 NVL72:~49 | B300:~6GB300 NVL72:~29 | B300:~4GB300 NVL72:~10 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.