OpenAI compatible API. Attested gateway. Public status.
Z.ai: GLM 5.1 Performance
TrustedRouter performance signals and provider route posture for Z.ai: GLM 5.1.
1 URLbase_url migration
100smodels and routes
0prompt logs by default
z-ai/glm-5.1
Performance
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), throughput, and success rate for Z.ai: GLM 5.1 — 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 | Throughput | Uptime | Config excluded | Samples |
|---|---|---|---|---|---|---|---|
| parasail | 908 ms | 1688 ms | 906 ms | — | 88.89% | — | 9 |
| venice | 1153 ms | 3301 ms | 1109 ms | — | 100.00% | — | 35 |
| zai | 2930 ms | 4838 ms | 2929 ms | — | 100.00% | — | 21 |
| phala | 3086 ms | 4624 ms | 2982 ms | — | 93.75% | — | 16 |
| tinfoil | 3562 ms | 11109 ms | 3457 ms | — | 61.11% | — | 72 |
| gmi | 4846 ms | 13482 ms | 4753 ms | — | 93.15% | — | 73 |
Full provider & model leaderboard.
Provider diversity
12 routes.
More routes give the auto router more room to fail over around provider 429 and 5xx responses.
Streaming
Gateway overhead is measured separately.
Public status separates TLS/health overhead from full model latency so slow LLMs do not inflate the router metric.
Status
Metadata rollups.
Status samples store latency, outcome, provider, model, route, cost, and region metadata only.
View public status or inspect provider routes.