Z.ai: GLM 4.7 Performance
TrustedRouter performance signals and provider route posture for Z.ai: GLM 4.7.
z-ai/glm-4.7
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), effective throughput, and success rate for Z.ai: GLM 4.7. 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 | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|---|
| atlas-cloud | 997 ms | 1066 ms | 997 ms | — | 100.00% | — | 2 |
| cerebras | 1276 ms | 7425 ms | 1276 ms | — | 100.00% | — | 13 |
| venice | 1363 ms | 1866 ms | 1363 ms | — | 100.00% | — | 4 |
| baseten | 1476 ms | 14383 ms | 1475 ms | — | 100.00% | — | 7 |
| deepinfra | 1874 ms | 1874 ms | 1873 ms | — | 100.00% | — | 1 |
| zai | 3231 ms | 28741 ms | 3231 ms | — | 90.91% | — | 11 |
Full provider & model leaderboard.
11 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.