DeepSeek R1 — H100 vs MI355X
Head-to-head AI inference benchmark comparison of H100 (NVIDIA Hopper) and MI355X (AMD CDNA 4) 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.
Near the low end of the 20–122 tok/s/user interactivity band, at 45 tok/s/user on DeepSeek R1: H100 runs 739 tok/s/chip at $0.44/M tokens, MI355X runs 2188 at $0.19/M. MI355X is 131% cheaper per token; MI355X delivers 196% more tok/s/chip.
Setting 71 tok/s/user as the target on DeepSeek R1, H100 produces 281 tok/s/chip ($1.16 per million tokens) and MI355X produces 1578 ($0.26). MI355X is 338% cheaper per token; MI355X delivers 462% more tok/s/chip.
At 97 tok/s/user interactivity on DeepSeek R1, H100 delivers 154 tok/s/chip at $2.11 per million tokens; MI355X delivers 1107 tok/s/chip at $0.38. MI355X is 459% cheaper per token; MI355X delivers 617% more tok/s/chip at this point. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | H100:739.5MI355X:2188.4 | H100:280.6MI355X:1577.7 | H100:154.3MI355X:1106.8 |
| Cost ($/M tok) | H100:$0.439MI355X:$0.190 | H100:$1.158MI355X:$0.264 | H100:$2.106MI355X:$0.376 |
| tok/s/MW | H100:539778MI355X:1047080 | H100:204852MI355X:754860 | H100:112644MI355X:529571 |
| Concurrency | H100:~132MI355X:~40 | H100:~41MI355X:~66 | H100:~17MI355X:~134 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
Total Tokens per $1 USD (Owning - Hyperscaler) vs. Interactivity
DeepSeek R1 0528 671B • FP4 • 8K / 1K • Source: SemiAnalysis InferenceX™
TCO $/chip/hr: H100: 1.17H200: 1.22B200: 1.73B300: 2.26GB200: 1.86GB300: 2.31MI300X: 0.95MI325X: 1.1MI355X: 1.5RTX6000PRO: 0.68
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.
No data available
Please change the model, sequence, precision, date range or chip selection.
Shift+Scroll to zoom • Drag to pan • Double-click to reset • Click a point to pin tooltip