DeepSeek V4 Pro 0813 1.6T · Chip comparison
DeepSeek V4 Pro 0813 1.6T — B200 vs B300
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and B300 (NVIDIA Blackwell) on DeepSeek V4 Pro 0813 1.6T. Latency, throughput, and cost across LLM workloads. 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 24–294 tok/s/user interactivity band, at 91 tok/s/user on DeepSeek V4 Pro 0813 1.6T: B200 runs 43,743 tok/s/chip at $0.011 per million tokens, B300 runs 51,936 at $0.012. B200 is 9% cheaper per token; B300 delivers 19% more tok/s/chip.
Setting 159 tok/s/user as the target on DeepSeek V4 Pro 0813 1.6T, B200 produces 14,626 tok/s/chip ($0.033 per million tokens) and B300 produces 11,002 ($0.057). B200 is 42% cheaper per token; B200 delivers 33% more tok/s/chip.
At 227 tok/s/user interactivity on DeepSeek V4 Pro 0813 1.6T, B200 delivers 4,054 tok/s/chip at $0.12 per million tokens; B300 delivers 3,569 tok/s/chip at $0.18. B200 is 33% cheaper per token; B200 delivers 14% more tok/s/chip at this point. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B20043,743B30051,936 | B20014,626B30011,002 | B2004,054B3003,569 |
| Cost ($/M tok) | B200$0.011B300$0.012 | B200$0.033B300$0.057 | B200$0.12B300$0.18 |
| tok/s/MW | B20025,580,718B30027,334,789 | B2008,553,292B3005,790,334 | B2002,370,542B3001,878,258 |
| Concurrency | B200~207B300~187 | B200~26B300~6 | B200~4B300~4 |