MiniMax M3.1 Flash 428B — GB300 NVL72 vs H200 Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus H200 (NVIDIA Hopper) on MiniMax M3.1 Flash 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 →
GB300 NVL72 edges H200 at 81 tok/s/user on MiniMax M3.1 Flash 428B — $0.01 per million tokens versus $0.03, a 211% cost-per-token gap.
Push MiniMax M3.1 Flash 428B to 152 tok/s/user and GB300 NVL72 lands at $0.01 per million tokens against H200's $0.05 — GB300 NVL72 pulls ahead by 329%.
GB300 NVL72: $0.02 per million tokens. H200: $0.08. Both at 223 tok/s/user on MiniMax M3.1 Flash 428B, with GB300 NVL72 283% cheaper. (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): GB300 NVL72 $2.31/chip/hr · H200 $1.22/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 | GB300 NVL72:$0.011H200:$0.034 | GB300 NVL72:$0.011H200:$0.048 | GB300 NVL72:$0.021H200:$0.080 |
| Concurrency | GB300 NVL72:~32H200:~16 | GB300 NVL72:~32H200:~10 | GB300 NVL72:~17H200:~5 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
No data available
No measurements to plot for this selection. Review the benchmark controls above or adjust quick filters.