Z.ai: GLM 5 Performance
Try GLM 5 on us. Starter credit covers your first requests, then one key reaches all 8 provider routes with automatic failover.
z-ai/glm-5
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), effective throughput, and success rate for Z.ai: GLM 5. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime, and no prompt or output content is stored.
| Provider | p50 TTFT | p95 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| atlas-cloud | 1479 ms | 1479 ms | — | 100.00% | — | 1 |
| venice | 1787 ms | 1864 ms | — | 100.00% | — | 2 |
| siliconflow | 2710 ms | 3046 ms | — | 100.00% | — | 3 |
| gmi | 3203 ms | 3676 ms | — | 100.00% | — | 2 |
| zai | 3283 ms | 4412 ms | — | 100.00% | — | 3 |
Full provider & model leaderboard.
8 routes.
More routes give the auto router more room to fail over around provider 429 and 5xx responses.
Gateway overhead is measured separately.
Public status separates TLS/health overhead from full model latency so slow LLMs do not inflate the router metric.
Metadata rollups.
Status samples store latency, outcome, provider, model, route, cost, and region metadata only.
View public status or inspect provider routes.