Z.ai: GLM 5.1 Performance
Compare measured TTFT, throughput, uptime, and route health for Z.ai: GLM 5.1 across TrustedRouter providers using metadata-only production probes.
z-ai/glm-5.1
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), 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 | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| friendli | 903 ms | 1431 ms | — | 100.00% | — | 3 |
| telnyx | 1717 ms | 1717 ms | — | 100.00% | — | 1 |
| siliconflow | 2599 ms | 2599 ms | — | 100.00% | — | 1 |
| gmi | 2672 ms | 4386 ms | — | 100.00% | — | 6 |
| phala | 2914 ms | 3003 ms | — | 66.67% | — | 3 |
| featherless | 2953 ms | 22661 ms | — | 100.00% | — | 2 |
| atlas-cloud | 3553 ms | 3553 ms | — | 100.00% | — | 1 |
| zai | 8619 ms | 10198 ms | — | 100.00% | — | 3 |
| chutes | 10194 ms | 11845 ms | — | 50.00% | — | 6 |
Full provider & model leaderboard.
12 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.