MiniMax M3 428B · Performance per Dollar

MiniMax M3 428B — H100 vs H200 Performance per Dollar

Cost per million tokens of H100 (NVIDIA Hopper) versus H200 (NVIDIA Hopper) 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 →

Near the low end of the 4–281 tok/s/user interactivity band — at 73 tok/s/user — H100 runs $0.56 per million tokens on MiniMax M3 428B while H200 runs $0.038. H200 is the cheaper choice by 93%.

On MiniMax M3 428B at 143 tok/s/user, the per-million math comes out to $0.56 for H100 and $0.043 for H200; H200 delivers 13× the total tokens per dollar.

At 212 tok/s/user on MiniMax M3 428B, H100 costs $0.56 per million tokens; H200 costs $0.087. H200 delivers 6.4× the tokens per dollar at this operating point. (Numbers reflect the default agentic-traces · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)

Chip pricing (owning hyperscaler): H100 $1.17/chip/hr · H200 $1.22/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
H100$0.56H200$0.038
H100$0.56H200$0.043
H100$0.56H200$0.087
Concurrency
H100~1H200~14
H100~1H200~11
H100~1H200~4
MiniMax M3 428B: H100 versus H200 cost per million tokens at matched interactivity levels
H100 versus H200 cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗