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 |
|---|---|---|---|---|---|---|---|
| digitalocean | 1341 ms | 4260 ms | 1341 ms | — | 100.00% | — | 3 |
| venice | 1678 ms | 13671 ms | 1677 ms | — | 100.00% | — | 3 |
| zai | 2243 ms | 4186 ms | 2243 ms | — | 100.00% | — | 5 |
| atlas-cloud | 2826 ms | 2826 ms | 2826 ms | — | 100.00% | — | 1 |
| gmi | 3313 ms | 24717 ms | 3312 ms | — | 100.00% | — | 13 |
| deepinfra | 3512 ms | 3752 ms | 3512 ms | — | 100.00% | — | 3 |
| siliconflow | 4458 ms | 5176 ms | 4458 ms | — | 100.00% | — | 5 |
| chutes | 1592 ms | 1592 ms | 1592 ms | — | 50.00% | 1 unsupported_route |
2 |
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.