GLM 5/5.1 · Performance per Dollar
GLM 5/5.1 — B200 vs MI355X Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) on GLM 5/5.1. 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.
B200 edges MI355X at 32 tok/s/user on GLM 5/5.1 — $0.27 per million tokens versus $0.30, a 10% lower cost per token.
Push GLM 5/5.1 to 51 tok/s/user and B200 lands at $0.37 per million tokens against MI355X's $0.44 — B200 costs 14% less.
B200: $0.48 per million tokens. MI355X: $0.59. Both at 71 tok/s/user on GLM 5/5.1, with B200 18% cheaper. (Numbers reflect the default 8k/1k · 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 · 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$0.27MI355X$0.30 | B200$0.37MI355X$0.44 | B200$0.48MI355X$0.59 |
| Concurrency | B200~240MI355X~19 | B200~23MI355X~9 | B200~13MI355X~4 |
