Muse Spark 1.3/Open 816B · Performance per dollar

Muse Spark 1.3/Open 816B — B200 vs MI355X performance per dollar

Cost per million tokens of B200 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) on Muse Spark 1.3/Open 816B. 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 →

At 182 tok/s/user on Muse Spark 1.3/Open 816B, B200 costs $0.021 per million tokens; MI355X costs $0.014. MI355X delivers 49% more tokens per dollar at this operating point.

MI355X edges B200 at 281 tok/s/user on Muse Spark 1.3/Open 816B — $0.029 per million tokens versus $0.038, a 26% lower cost per token.

Push Muse Spark 1.3/Open 816B to 380 tok/s/user and B200 lands at $0.064 per million tokens against MI355X's $0.049 — MI355X costs 23% less. (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$0.021MI355X$0.014
B200$0.038MI355X$0.029
B200$0.064MI355X$0.049
Concurrency
B200~15MI355X~28
B200~7MI355X~23
B200~9MI355X~10
Muse Spark 1.3/Open 816B: 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 ↗