Z.ai: GLM 5 Performance
TrustedRouter performance signals and provider route posture for Z.ai: GLM 5.
z-ai/glm-5
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), 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 | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|---|
| deepinfra | 742 ms | 3512 ms | 742 ms | — | 100.00% | — | 2 |
| digitalocean | 1341 ms | 1341 ms | 1341 ms | — | 100.00% | — | 1 |
| venice | 2016 ms | 13671 ms | 2016 ms | — | 100.00% | — | 4 |
| zai | 2243 ms | 2526 ms | 2243 ms | — | 100.00% | — | 3 |
| atlas-cloud | 2826 ms | 2826 ms | 2826 ms | — | 100.00% | — | 1 |
| gmi | 3677 ms | 24717 ms | 3676 ms | — | 100.00% | — | 7 |
| siliconflow | 4135 ms | 4458 ms | 4135 ms | — | 100.00% | — | 3 |
Full provider & model leaderboard.
14 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.