MiniMax M3 428B · Performance per dollar

MiniMax M3 428B — MI355X vs Vera Rubin NVL72 performance per dollar

Cost per million tokens of MI355X (AMD CDNA 4) 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 →

On MiniMax M3 428B at 194 tok/s/user, the per-million math comes out to $0.013 for MI355X and $0.007 for Vera Rubin NVL72; Vera Rubin NVL72 delivers 96% more total tokens per dollar.

At 286 tok/s/user on MiniMax M3 428B, MI355X costs $0.025 per million tokens; Vera Rubin NVL72 costs $0.008. Vera Rubin NVL72 delivers 3.0× the tokens per dollar at this operating point.

Vera Rubin NVL72 edges MI355X at 377 tok/s/user on MiniMax M3 428B — $0.012 per million tokens versus $0.046, a 74% lower cost per token. (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): MI355X $1.50/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
MI355X$0.013Vera Rubin NVL72$0.007
MI355X$0.025Vera Rubin NVL72$0.008
MI355X$0.046Vera Rubin NVL72$0.012
Concurrency
MI355X~18Vera Rubin NVL72~43
MI355X~9Vera Rubin NVL72~35
MI355X~4Vera Rubin NVL72~23
MiniMax M3 428B: MI355X versus Vera Rubin NVL72 cost per million tokens at matched interactivity levels
MI355X 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 ↗