DeepSeekv4 Pro 0813 1.6T — B300 vs MI355X Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) on DeepSeekv4 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.
Push DeepSeekv4 Pro 0813 1.6T to 36 tok/s/user and B300 lands at $0.11 per million tokens against MI355X's $0.30 — B300 pulls ahead by 160%.
B300: $0.89 per million tokens. MI355X: $1.34. Both at 67 tok/s/user on DeepSeekv4 Pro 0813 1.6T, with B300 50% cheaper.
Toward the upper edge of the 6–127 tok/s/user interactivity band — at 97 tok/s/user — B300 runs $1.36 per million tokens on DeepSeekv4 Pro 0813 1.6T while MI355X runs $2.08. B300 is the cheaper choice by 53%. (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.)
Chip pricing (owning hyperscaler): B300 $2.26/chip/hr · MI355X $1.50/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | B300:$0.115MI355X:$0.297 | B300:$0.889MI355X:$1.337 | B300:$1.358MI355X:$2.078 |
| Concurrency | B300:~907MI355X:~176 | B300:~21MI355X:~20 | B300:~10MI355X:~9 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
DeepSeek V4 Pro 0813 1.6T 8K / 1K Cost per Million Total Tokens vs. Interactivity
DeepSeek V4 Pro 0813 1.6T 8K / 1K Cost per Million Total Tokens vs. Interactivity- Cost Tier:
- Source:
- SemiAnalysis InferenceX™
TCO $/chip/hr:
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
Matching measurements exist, but their chip series are hidden.
Shift+Scroll to zoom • Drag to pan • Double-click to reset • Click a point to pin tooltip
1 The ATOM engine is promising, however it has yet to serve production tokens. It is still in its infant stage.