MiniMax M3 428B · Performance per dollar
MiniMax M3 428B — GB200 NVL72 vs MI355X performance per dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) 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 →
Push MiniMax M3 428B to 168 tok/s/user and GB200 NVL72 lands at $0.015 per million tokens against MI355X's $0.011 — MI355X costs 31% less.
GB200 NVL72: $0.032 per million tokens. MI355X: $0.021. Both at 253 tok/s/user on MiniMax M3 428B, with MI355X 33% cheaper.
Toward the upper edge of the 83–423 tok/s/user interactivity band — at 338 tok/s/user — GB200 NVL72 runs $0.063 per million tokens on MiniMax M3 428B while MI355X runs $0.042. MI355X is the cheaper choice by 33%. (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): GB200 NVL72 $1.86/chip/hr · MI355X $1.50/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 | GB200 NVL72$0.015MI355X$0.011 | GB200 NVL72$0.032MI355X$0.021 | GB200 NVL72$0.063MI355X$0.042 |
| Concurrency | GB200 NVL72~19MI355X~21 | GB200 NVL72~9MI355X~12 | GB200 NVL72~2MI355X~5 |
