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 |
|---|---|---|---|---|---|---|---|
| friendli | 2457 ms | 3438 ms | 2457 ms | — | 100.00% | — | 24 |
| wafer | 2737 ms | 5623 ms | 2737 ms | — | 100.00% | — | 41 |
| venice | 3037 ms | 7787 ms | 3036 ms | — | 100.00% | — | 16 |
| parasail | 3412 ms | 19931 ms | 3412 ms | — | 100.00% | — | 7 |
| crusoe | 3693 ms | 5638 ms | 3693 ms | — | 100.00% | — | 23 |
| gmi | 3850 ms | 4806 ms | 3850 ms | — | 100.00% | — | 48 |
| zai | 6478 ms | 9063 ms | 6477 ms | — | 100.00% | — | 24 |
| alibaba | — | — | — | — | 0.00% | — | 2 |
| atlas-cloud | — | — | — | — | 0.00% | — | 4 |
| chutes | — | — | — | — | 0.00% | — | 20 |
| digitalocean | — | — | — | — | 0.00% | — | 8 |
| telnyx | — | — | — | — | 0.00% | — | 15 |
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.