GLM 5.3 744B — B300 vs MI355X Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) on GLM 5.3 744B. Owning-hyperscaler TCO normalized by output 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 →
B300: $0.05 per million tokens. MI355X: $0.15. Both at 133 tok/s/user on GLM 5.3 744B, with B300 185% cheaper.
Around the middle of the 126–157 tok/s/user interactivity band — at 142 tok/s/user — B300 runs $0.06 per million tokens on GLM 5.3 744B while MI355X runs $0.22. B300 is the cheaper choice by 274%.
On GLM 5.3 744B at 150 tok/s/user, the per-million math comes out to $0.07 for B300 and $0.24 for MI355X; B300 delivers 254% more output 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): B300 $2.26/chip/hr · MI355X $1.50/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | B300:$0.053MI355X:$0.151 | B300:$0.060MI355X:$0.224 | B300:$0.067MI355X:$0.238 |
| Concurrency | B300:~16MI355X:~2 | B300:~15MI355X:~2 | B300:~14MI355X:~2 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.