Qwen 3.5 397B-A17B · Performance per Dollar

Qwen 3.5 397B-A17B — B200 vs MI325X Performance per Dollar

Cost per million tokens of B200 (NVIDIA Blackwell) versus MI325X (AMD CDNA 3) on Qwen 3.5 397B-A17B. 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 →

Near the low end of the 11–58 tok/s/user interactivity band — at 22 tok/s/user — B200 runs $0.013 per million tokens on Qwen 3.5 397B-A17B while MI325X runs $0.022. B200 is the cheaper choice by 43%.

On Qwen 3.5 397B-A17B at 34 tok/s/user, the per-million math comes out to $0.013 for B200 and $0.029 for MI325X; B200 delivers 126% more total tokens per dollar.

At 46 tok/s/user on Qwen 3.5 397B-A17B, B200 costs $0.013 per million tokens; MI325X costs $0.039. B200 delivers 3.0× the tokens per dollar at this operating point. (Numbers reflect the default agentic-traces · fp8 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 · MI325X $1.10/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.

View full latency and throughput comparison →

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$0.013MI325X$0.022
B200$0.013MI325X$0.029
B200$0.013MI325X$0.039
Concurrency
B200~32MI325X~47
B200~32MI325X~24
B200~32MI325X~8
Qwen 3.5 397B-A17B: B200 versus MI325X cost per million tokens at matched interactivity levels
B200 versus MI325X cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗