DeepSeek V4.1 Flash 552B — B200 vs H100 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus H100 (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 119 tok/s/user and B200 lands at $0.00 per million tokens against H100's $0.02 — B200 pulls ahead by 1315%.
B200: $0.00 per million tokens. H100: $0.04. Both at 179 tok/s/user on DeepSeek V4.1 Flash 552B, with B200 1459% cheaper.
Toward the upper edge of the 60–297 tok/s/user interactivity band — at 238 tok/s/user — B200 runs $0.00 per million tokens on DeepSeek V4.1 Flash 552B while H100 runs $0.08. B200 is the cheaper choice by 1767%. (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): B200 $1.73/chip/hr · H100 $1.17/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:$0.001H100:$0.021 | B200:$0.003H100:$0.043 | B200:$0.004H100:$0.076 |
| Concurrency | B200:~228H100:~18 | B200:~114H100:~8 | B200:~63H100:~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.