DeepSeek V4.1 Flash 552B — H100 vs H200 Performance per Dollar
Cost per million tokens of H100 (NVIDIA Hopper) versus H200 (NVIDIA Hopper) on DeepSeek V4.1 Flash 552B. 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 DeepSeek V4.1 Flash 552B to 213 tok/s/user and H100 lands at $0.11 per million tokens against H200's $0.09 — H200 pulls ahead by 27%.
H100: $0.13 per million tokens. H200: $0.09. Both at 216 tok/s/user on DeepSeek V4.1 Flash 552B, with H200 47% cheaper.
Toward the upper edge of the 210–221 tok/s/user interactivity band — at 219 tok/s/user — H100 runs $0.13 per million tokens on DeepSeek V4.1 Flash 552B while H200 runs $0.09. H200 is the cheaper choice by 47%. (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): H100 $1.17/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 | H100:$0.109H200:$0.085 | H100:$0.127H200:$0.086 | H100:$0.129H200:$0.087 |
| Concurrency | H100:~3H200:~4 | H100:~2H200:~4 | H100:~2H200:~4 |
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.