Head-to-head AI inference benchmark comparison of GB200 NVL72 (NVIDIA Blackwell) and H100 (NVIDIA Hopper) on DeepSeek R1. 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.
GB200 NVL72 posts 6310 tok/s/chip for $0.08 per million tokens at 54 tok/s/user on DeepSeek R1; H100 posts 554 tok/s/chip for $0.59. GB200 NVL72 is 617% cheaper per token; GB200 NVL72 delivers 1039% more tok/s/chip.
Throughput at 77 tok/s/user on DeepSeek R1: GB200 NVL72 hits 5707 tok/s/chip, H100 hits 224. Per-million costs land at $0.09 and $1.45 respectively. GB200 NVL72 is 1505% cheaper per token; GB200 NVL72 delivers 2451% more tok/s/chip.
GB200 NVL72 / H100 on DeepSeek R1 at 100 tok/s/user: 4728 / 149 tok/s/chip, $0.11 / $2.18 per million tokens. GB200 NVL72 is 1892% cheaper per token; GB200 NVL72 delivers 3066% more tok/s/chip. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | GB200 NVL72:6309.9H100:553.9 | GB200 NVL72:5707.2H100:223.7 | GB200 NVL72:4728.1H100:149.3 |
| Cost ($/M tok) | GB200 NVL72:$0.082H100:$0.587 | GB200 NVL72:$0.091H100:$1.453 | GB200 NVL72:$0.109H100:$2.176 |
| tok/s/MW | GB200 NVL72:3374298H100:404284 | GB200 NVL72:3051998H100:163312 | GB200 NVL72:2528416H100:109006 |
| Concurrency | GB200 NVL72:~1554H100:~95 | GB200 NVL72:~588H100:~31 | GB200 NVL72:~333H100:~16 |
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
TCO $/chip/hr: VR200: 3.61H100: 1.17H200: 1.22B200: 1.73B300: 2.26GB200: 1.86GB300: 2.31MI300X: 0.95MI325X: 1.1MI355X: 1.5RTX6000PRO: 0.68Jalapeño (Teacup): 1.47
Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate cost per million tokens per decode chip or per prefill chip, rather than per total chip count. This makes direct token cost comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate input throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct input throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate output throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct output throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate power per decode chip or per prefill chip, rather than per total chip count. This makes direct power comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate Joules per decode chip or per prefill chip, rather than per total chip count. This makes direct Joules per token comparison with aggregated configs not an apples-to-apples comparison.
Matching measurements exist, but their chip series are hidden.
Shift+Scroll to zoom • Drag to pan • Double-click to reset • Click a point to pin tooltip
DeepSeek R1 0528 671B 8K / 1K Total Tokens per $1 TCO vs. Interactivity