DeepSeek V4 Pro 1.6T — B300 vs MI355X Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) on DeepSeek V4 Pro 1.6T. Owning-hyperscaler TCO normalized by output 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.
Push DeepSeek V4 Pro 1.6T to 40 tok/s/user and B300 lands at $0.13 per million tokens against MI355X's $0.25 — B300 pulls ahead by 97%.
B300: $0.30 per million tokens. MI355X: $0.52. Both at 77 tok/s/user on DeepSeek V4 Pro 1.6T, with B300 74% cheaper.
Toward the upper edge of the 4–150 tok/s/user interactivity band — at 114 tok/s/user — B300 runs $0.44 per million tokens on DeepSeek V4 Pro 1.6T while MI355X runs $1.42. B300 is the cheaper choice by 219%. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
GPU pricing (owning hyperscaler): B300 $2.34/GPU/hr · MI355X $1.48/GPU/hr. Source: SemiAnalysis Market August 2025 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | B300:$0.126MI355X:$0.247 | B300:$0.301MI355X:$0.525 | B300:$0.444MI355X:$1.416 |
| Concurrency | B300:~1024MI355X:~68 | B300:~15MI355X:~10 | B300:~7MI355X:~3 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.