DeepSeek V4 Pro 0813 1.6T · Chip comparison

DeepSeek V4 Pro 0813 1.6T — H200 vs MI355X

Head-to-head AI inference benchmark comparison of H200 (NVIDIA Hopper) and MI355X (AMD CDNA 4) 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 →

MI355X hits 75,262 tok/s/chip for $0.006 per million tokens at 66 tok/s/user on DeepSeek V4 Pro 0813 1.6T. No H200 data at this operating point.

MI355X: 22,800 tok/s/chip, $0.018 per million tokens at 127 tok/s/user on DeepSeek V4 Pro 0813 1.6T. H200 is unmeasured here.

At 188 tok/s/user on DeepSeek V4 Pro 0813 1.6T, MI355X delivers 8,098 tok/s/chip at $0.051 per million tokens; H200 hasn't been benchmarked at this target. (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)
H200—MI355X75,262
H200—MI355X22,800
H200—MI355X8,098
Cost ($/M tok)
H200—MI355X$0.006
H200—MI355X$0.018
H200—MI355X$0.051
tok/s/MW
H200—MI355X36,010,659
H200—MI355X10,908,914
H200—MI355X3,874,730
Concurrency
H200—MI355X~368
H200—MI355X~48
H200—MI355X~14