OpenAI compatible API · Attested · Public status
Z.ai: GLM 4.6 Performance
TrustedRouter performance signals and provider route posture for Z.ai: GLM 4.6.
Onebase URL to migrate
100sof models and routes
Noneprompt logs by default
z-ai/glm-4.6
open weights
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 4.6 — 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 | 3196 ms | 13535 ms | 3195 ms | — | 100.00% | — | 14 |
| zai | 3560 ms | 17207 ms | 3559 ms | — | 92.31% | — | 13 |
| atlas-cloud | 3935 ms | 23431 ms | 3935 ms | — | 100.00% | — | 5 |
| deepinfra | 8301 ms | 9271 ms | 8301 ms | — | 100.00% | — | 2 |
Full provider & model leaderboard.
Provider diversity
7 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.