OpenAI compatible API. Attested gateway. Public status.
Z.ai: GLM 4.7 Performance
TrustedRouter performance signals and provider route posture for Z.ai: GLM 4.7.
1 URLbase_url migration
100smodels and routes
0prompt logs by default
z-ai/glm-4.7
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 4.7 — 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 |
|---|---|---|---|---|---|---|---|
| cerebras | 1018 ms | 2556 ms | 920 ms | — | 100.00% | — | 91 |
| venice | 1443 ms | 3352 ms | 1351 ms | — | 100.00% | — | 32 |
| phala | 1993 ms | 2900 ms | 1991 ms | — | 100.00% | — | 19 |
| zai | 2155 ms | 2720 ms | 2102 ms | — | 90.91% | — | 33 |
| parasail | 6293 ms | 8687 ms | 6190 ms | — | 85.71% | — | 7 |
Full provider & model leaderboard.
Provider diversity
10 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.