Kimi K3 2.8T · Performance per dollar
Kimi K3 2.8T — B200 vs MI355X performance per dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) on Kimi K3 2.8T. 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 →
B200: $0.089 per million tokens. MI355X: $0.046. Both at 57 tok/s/user on Kimi K3 2.8T, with MI355X 48% cheaper.
Around the middle of the 15–186 tok/s/user interactivity band — at 100 tok/s/user — B200 runs $0.18 per million tokens on Kimi K3 2.8T while MI355X runs $0.077. MI355X is the cheaper choice by 57%.
On Kimi K3 2.8T at 144 tok/s/user, the per-million math comes out to $0.27 for B200 and $0.15 for MI355X; MI355X delivers 88% more total tokens per dollar. (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.
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$0.089MI355X$0.046 | B200$0.18MI355X$0.077 | B200$0.27MI355X$0.15 |
| Concurrency | B200~18MI355X~16 | B200~7MI355X~24 | B200~5MI355X~4 |
