MiniMax M3 428B · Performance per dollar

MiniMax M3 428B — H200 vs Vera Rubin NVL72 performance per dollar

Cost per million tokens of H200 (NVIDIA Hopper) 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 →

At 314 tok/s/user on MiniMax M3 428B, Vera Rubin NVL72 comes in at $0.009 per million tokens. H200 hasn't been benchmarked at this operating point.

Only Vera Rubin NVL72 has cost data at 527 tok/s/user on MiniMax M3 428B — $0.026 per million tokens. H200 is unmeasured at this target.

Vera Rubin NVL72 costs $0.036 per million tokens at 740 tok/s/user on MiniMax M3 428B; we have no H200 benchmark data at this exact 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): H200 $1.22/chip/hr · Vera Rubin NVL72 $3.61/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.

View full latency and throughput comparison →

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
H200—Vera Rubin NVL72$0.009
H200—Vera Rubin NVL72$0.026
H200—Vera Rubin NVL72$0.036
Concurrency
H200—Vera Rubin NVL72~32
H200—Vera Rubin NVL72~52
H200—Vera Rubin NVL72~37
MiniMax M3 428B: H200 versus Vera Rubin NVL72 cost per million tokens at matched interactivity levels
H200 versus Vera Rubin NVL72 cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗