Z.ai: GLM 5.1 Performance
TrustedRouter performance signals and provider route posture for Z.ai: GLM 5.1.
z-ai/glm-5.1
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 5.1. 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 |
|---|---|---|---|---|---|---|---|
| wafer | 1391 ms | 14124 ms | 1391 ms | — | 100.00% | — | 15 |
| digitalocean | 1554 ms | 10652 ms | 1553 ms | — | 100.00% | — | 4 |
| telnyx | 1590 ms | 3844 ms | 1590 ms | — | 100.00% | — | 2 |
| siliconflow | 1768 ms | 4618 ms | 1768 ms | — | 100.00% | — | 4 |
| chutes | 2027 ms | 4202 ms | 2027 ms | — | 100.00% | — | 4 |
| crusoe | 2205 ms | 2205 ms | 2205 ms | — | 100.00% | — | 1 |
| gmi | 2433 ms | 5076 ms | 2433 ms | — | 100.00% | — | 7 |
| friendli | 2458 ms | 4244 ms | 2458 ms | — | 100.00% | — | 5 |
| venice | 2834 ms | 6654 ms | 2833 ms | — | 100.00% | — | 9 |
| atlas-cloud | 2975 ms | 2975 ms | 2975 ms | — | 100.00% | 1 router_error |
1 |
| zai | 3024 ms | 7914 ms | 3024 ms | — | 100.00% | — | 5 |
Full provider & model leaderboard.
24 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.