DeepSeek V4 Pro 0813 1.6T · Chip comparison

DeepSeek V4 Pro 0813 1.6T — GB300 NVL72 vs H200

Head-to-head AI inference benchmark comparison of GB300 NVL72 (NVIDIA Blackwell) and H200 (NVIDIA Hopper) 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 →

GB300 NVL72: 82,770 tok/s/chip, $0.008 per million tokens at 103 tok/s/user on DeepSeek V4 Pro 0813 1.6T. H200 is unmeasured here.

At 168 tok/s/user on DeepSeek V4 Pro 0813 1.6T, GB300 NVL72 delivers 21,937 tok/s/chip at $0.029 per million tokens; H200 hasn't been benchmarked at this target.

GB300 NVL72 hits 6,029 tok/s/chip for $0.11 per million tokens at 234 tok/s/user on DeepSeek V4 Pro 0813 1.6T. No H200 data at this operating 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.)

View performance per dollar →

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)
GB300 NVL7282,770H200—
GB300 NVL7221,937H200—
GB300 NVL726,029H200—
Cost ($/M tok)
GB300 NVL72$0.008H200—
GB300 NVL72$0.029H200—
GB300 NVL72$0.11H200—
tok/s/MW
GB300 NVL7239,042,251H200—
GB300 NVL7210,347,553H200—
GB300 NVL722,843,798H200—
Concurrency
GB300 NVL72~415H200—
GB300 NVL72~80H200—
GB300 NVL72~2H200—