DeepSeek V4 Pro 0813 1.6T · Performance per Dollar

DeepSeek V4 Pro 0813 1.6T — B200 vs B300 Performance per Dollar

Cost per million tokens of B200 (NVIDIA Blackwell) versus B300 (NVIDIA Blackwell) on DeepSeek V4 Pro 0813 1.6T. 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 →

B200 edges B300 at 91 tok/s/user on DeepSeek V4 Pro 0813 1.6T — $0.011 per million tokens versus $0.012, a 9% lower cost per token.

Push DeepSeek V4 Pro 0813 1.6T to 159 tok/s/user and B200 lands at $0.033 per million tokens against B300's $0.057 — B200 costs 42% less.

B200: $0.12 per million tokens. B300: $0.18. Both at 227 tok/s/user on DeepSeek V4 Pro 0813 1.6T, with B200 33% 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): B200 $1.73/chip/hr · B300 $2.26/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.

View full latency and throughput comparison →

B300 vs B200: full specs & benchmarks across models →

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
B200$0.011B300$0.012
B200$0.033B300$0.057
B200$0.12B300$0.18
Concurrency
B200~207B300~187
B200~26B300~6
B200~4B300~4
DeepSeek V4 Pro 0813 1.6T: B200 versus B300 cost per million tokens at matched interactivity levels
B200 versus B300 cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗