MiniMax M3 428B · Performance per dollar
MiniMax M3 428B — GB300 NVL72 vs Vera Rubin NVL72 performance per dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus Vera Rubin NVL72 (NVIDIA Vera Rubin) 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 →
Vera Rubin NVL72 edges GB300 NVL72 at 160 tok/s/user on MiniMax M3 428B — $0.006 per million tokens versus $0.020, a 68% lower cost per token.
Push MiniMax M3 428B to 219 tok/s/user and GB300 NVL72 lands at $0.030 per million tokens against Vera Rubin NVL72's $0.007 — Vera Rubin NVL72 costs 75% less.
GB300 NVL72: $0.050 per million tokens. Vera Rubin NVL72: $0.008. Both at 278 tok/s/user on MiniMax M3 428B, with Vera Rubin NVL72 84% 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): GB300 NVL72 $2.31/chip/hr · Vera Rubin NVL72 $3.61/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
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) |
|---|---|---|---|
| Dollars per million tokens | GB300 NVL72$0.020Vera Rubin NVL72$0.006 | GB300 NVL72$0.030Vera Rubin NVL72$0.007 | GB300 NVL72$0.050Vera Rubin NVL72$0.008 |
| Concurrency | GB300 NVL72~28Vera Rubin NVL72~48 | GB300 NVL72~20Vera Rubin NVL72~40 | GB300 NVL72~24Vera Rubin NVL72~35 |
