DeepSeek V4 Pro 0813 1.6T · Performance per Dollar

DeepSeek V4 Pro 0813 1.6T — B200 vs MI355X Performance per Dollar

Cost per million tokens of B200 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) on DeepSeek V4 Pro 0813 1.6T. Large-hyperscaler-volume ownership TCO normalized by total tokens — performance per dollar across LLM workloads. Pick the more cost-efficient SKU at every target interactivity level. 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 →

B200: $0.010 per million tokens. MI355X: $0.007. Both at 80 tok/s/user on DeepSeek V4 Pro 0813 1.6T, with MI355X 33% cheaper.

Around the middle of the 24–248 tok/s/user interactivity band — at 136 tok/s/user — B200 runs $0.024 per million tokens on DeepSeek V4 Pro 0813 1.6T while MI355X runs $0.019. MI355X is the cheaper choice by 19%.

On DeepSeek V4 Pro 0813 1.6T at 192 tok/s/user, the per-million math comes out to $0.077 for B200 and $0.057 for MI355X; MI355X delivers 36% more total tokens per dollar. (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.)

Chip pricing (owning hyperscaler): B200 $1.73/chip/hr · MI355X $1.50/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.

View full latency and throughput comparison →

MI355X vs B200: full specs & benchmarks across models →

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)
Dollars per Million Tokens
B200$0.010MI355X$0.007
B200$0.024MI355X$0.019
B200$0.077MI355X$0.057
Concurrency
B200~255MI355X~234
B200~47MI355X~43
B200~8MI355X~13
DeepSeek V4 Pro 0813 1.6T: B200 versus MI355X cost per million tokens at matched interactivity levels
B200 versus MI355X cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗