MiniMax M3 428B — GB300 NVL72 vs H100 Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus H100 (NVIDIA Hopper) on MiniMax M3 428B. 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 →
H100 costs $0.42 per million tokens at 7 tok/s/user on MiniMax M3 428B; we have no GB300 NVL72 benchmark data at this exact target.
At 11 tok/s/user on MiniMax M3 428B, H100 comes in at $0.49 per million tokens. GB300 NVL72 hasn't been benchmarked at this operating point.
Only H100 has cost data at 15 tok/s/user on MiniMax M3 428B — $0.51 per million tokens. GB300 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): GB300 NVL72 $2.31/chip/hr · H100 $1.17/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:—H100:$0.417 | GB300 NVL72:—H100:$0.493 | GB300 NVL72:—H100:$0.510 |
| Concurrency | GB300 NVL72:—H100:~6 | GB300 NVL72:—H100:~3 | GB300 NVL72:—H100:~1 |