MiniMax M3 428B β MI300X vs MI325X Performance per Dollar
Cost per million tokens of MI300X (AMD CDNA 3) versus MI325X (AMD CDNA 3) on MiniMax M3 428B. Large-hyperscaler-volume ownership TCO normalized by total tokens β 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 β 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 β
Push MiniMax M3 428B to 28 tok/s/user and MI300X lands at $0.05 per million tokens against MI325X's $0.33 β MI300X pulls ahead by 519%.
MI300X: $0.05 per million tokens. MI325X: $0.34. Both at 29 tok/s/user on MiniMax M3 428B, with MI300X 538% cheaper.
Toward the upper edge of the 28β30 tok/s/user interactivity band β at 30 tok/s/user β MI300X runs $0.05 per million tokens on MiniMax M3 428B while MI325X runs $0.35. MI300X is the cheaper choice by 560%. (Numbers reflect the default agentic-traces Β· fp8 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): MI300X $0.95/chip/hr Β· MI325X $1.10/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 | MI300X:$0.053MI325X:$0.325 | MI300X:$0.053MI325X:$0.335 | MI300X:$0.053MI325X:$0.347 |
| Concurrency | MI300X:~10MI325X:~2 | MI300X:~10MI325X:~2 | MI300X:~10MI325X:~1 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.