GLM 5/5.1 · Performance per Dollar
GLM 5/5.1 — B300 vs MI325X Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus MI325X (AMD CDNA 3) 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.
On GLM 5/5.1 at 14 tok/s/user, the per-million math comes out to $0.38 for B300 and $0.62 for MI325X; B300 delivers 64% more total tokens per dollar.
At 19 tok/s/user on GLM 5/5.1, B300 costs $0.40 per million tokens; MI325X costs $0.99. B300 delivers 144% more tokens per dollar at this operating point.
B300 edges MI325X at 24 tok/s/user on GLM 5/5.1 — $0.43 per million tokens versus $1.53, a 72% lower cost per token. (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): B300 $2.26/chip/hr · MI325X $1.10/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 | B300$0.38MI325X$0.62 | B300$0.40MI325X$0.99 | B300$0.43MI325X$1.53 |
| Concurrency | B300~107MI325X~34 | B300~75MI325X~15 | B300~56MI325X~8 |
