GLM 5.3 744B · Performance per Dollar

GLM 5.3 744B — TPU7x vs Vera Rubin NVL72 Performance per Dollar

Cost per million tokens of TPU7x (Google Ironwood) versus Vera Rubin NVL72 (NVIDIA Vera Rubin) on GLM 5.3 744B. 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.

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 →

TPU7x costs $0.04 per million tokens at 92 tok/s/user on GLM 5.3 744B; we have no Vera Rubin NVL72 benchmark data at this exact target.

At 164 tok/s/user on GLM 5.3 744B, TPU7x comes in at $0.05 per million tokens. Vera Rubin NVL72 hasn't been benchmarked at this operating point.

Only TPU7x has cost data at 237 tok/s/user on GLM 5.3 744B — $0.08 per million tokens. Vera Rubin NVL72 is unmeasured at this target. (Numbers reflect the default agentic-traces · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)

Chip pricing (owning hyperscaler): TPU7x $1.03/chip/hr · Vera Rubin NVL72 $3.61/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.

View full latency + throughput comparison →

GLM 5.3 744B: TPU7x versus Vera Rubin NVL72 cost per million tokens at matched interactivity levels
TPU7x versus Vera Rubin NVL72 cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
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)
Dollar per Million Tokens
TPU7x:$0.036Vera Rubin NVL72:—
TPU7x:$0.052Vera Rubin NVL72:—
TPU7x:$0.081Vera Rubin NVL72:—
Concurrency
TPU7x:~12Vera Rubin NVL72:—
TPU7x:~6Vera Rubin NVL72:—
TPU7x:~3Vera Rubin NVL72:—