OpenAI compatible API. Attested gateway. Public status.
Z.ai: GLM 5 Performance
TrustedRouter performance signals and provider route posture for Z.ai: GLM 5.
1 URLbase_url migration
100smodels and routes
0prompt logs by default
z-ai/glm-5
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 — 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 |
|---|---|---|---|---|---|---|---|
| venice | 1448 ms | 2786 ms | 1349 ms | — | 100.00% | — | 35 |
| siliconflow | 1705 ms | 2754 ms | 1640 ms | — | 100.00% | — | 43 |
| zai | 2858 ms | 7370 ms | 2766 ms | — | 100.00% | — | 25 |
| phala | 2947 ms | 16618 ms | 2843 ms | — | 81.82% | — | 22 |
| gmi | 3861 ms | 12930 ms | 3757 ms | — | 77.94% | — | 68 |
Full provider & model leaderboard.
Provider diversity
11 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.