MiniMax M3 428B β B200 vs MI325X Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) 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
Only B200 has cost data at 178 tok/s/user on MiniMax M3 428B β $0.01 per million tokens. MI325X is unmeasured at this target.
B200 costs $0.02 per million tokens at 291 tok/s/user on MiniMax M3 428B; we have no MI325X benchmark data at this exact target.
At 405 tok/s/user on MiniMax M3 428B, B200 comes in at $0.03 per million tokens. MI325X hasn't been benchmarked at this operating point. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): B200 $1.73/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 | B200:$0.014MI325X:β | B200:$0.017MI325X:β | B200:$0.029MI325X:β |
| Concurrency | B200:~20MI325X:β | B200:~20MI325X:β | B200:~11MI325X:β |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.