GLM 5.3 744B — B300 vs TPU7x Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus TPU7x (Google Ironwood) 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 →
B300 costs $0.03 per million tokens at 95 tok/s/user on GLM 5.3 744B; we have no TPU7x benchmark data at this exact target.
At 172 tok/s/user on GLM 5.3 744B, B300 comes in at $0.06 per million tokens. TPU7x hasn't been benchmarked at this operating point.
Only B300 has cost data at 250 tok/s/user on GLM 5.3 744B — $0.11 per million tokens. TPU7x 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): B300 $2.26/chip/hr · TPU7x $1.03/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:$0.035TPU7x:— | B300:$0.064TPU7x:— | B300:$0.106TPU7x:— |
| Concurrency | B300:~22TPU7x:— | B300:~13TPU7x:— | B300:~2TPU7x:— |