DeepSeek V4.1 Flash 552B — B300 vs H100 Performance per Dollar
Cost per million tokens of B300 (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 →
B300: $0.03 per million tokens. H100: $0.13. Both at 226 tok/s/user on DeepSeek V4.1 Flash 552B, with B300 279% cheaper.
Around the middle of the 210–275 tok/s/user interactivity band — at 243 tok/s/user — B300 runs $0.04 per million tokens on DeepSeek V4.1 Flash 552B while H100 runs $0.13. B300 is the cheaper choice by 241%.
On DeepSeek V4.1 Flash 552B at 259 tok/s/user, the per-million math comes out to $0.04 for B300 and $0.13 for H100; B300 delivers 203% more total tokens per dollar. (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): B300 $2.26/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 | B300:$0.034H100:$0.130 | B300:$0.038H100:$0.131 | B300:$0.043H100:$0.132 |
| Concurrency | B300:~10H100:~2 | B300:~9H100:~1 | B300:~8H100:~1 |
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.