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 36 tok/s/user and B300 lands at $0.42 per million tokens against MI355X's $0.50 — B300 pulls ahead by 19%.
B300: $1.48 per million tokens. MI355X: $1.30. Both at 67 tok/s/user on DeepSeek V4 Pro 1.6T, with MI355X 14% cheaper.
Toward the upper edge of the 6–127 tok/s/user interactivity band — at 97 tok/s/user — B300 runs $2.59 per million tokens on DeepSeek V4 Pro 1.6T while MI355X runs $2.03. MI355X is the cheaper choice by 27%. (Numbers reflect the default 1k/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:$0.417MI355X:$0.498 | B300:$1.478MI355X:$1.301 | B300:$2.590MI355X:$2.032 |
| Concurrency | B300:~90MI355X:~107 | B300:~13MI355X:~21 | B300:~6MI355X:~9 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.