OpenAI compatible API · Attested · Public status
Z.ai: GLM 4.7 Performance
TrustedRouter performance signals and provider route posture for Z.ai: GLM 4.7.
Onebase URL to migrate
100sof models and routes
Noneprompt logs by default
z-ai/glm-4.7
open weights
Performance
AI IQ
IQ 102
#55 public AI IQ rank for glm-4.7
View AI IQ profile
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 |
|---|---|---|---|---|---|---|---|
| deepinfra | 1004 ms | 1004 ms | 1003 ms | — | 100.00% | 3 unsupported_route |
1 |
| venice | 2450 ms | 15968 ms | 2450 ms | — | 100.00% | — | 11 |
| atlas-cloud | 3672 ms | 19904 ms | 3672 ms | — | 100.00% | — | 7 |
| baseten | 3843 ms | 13185 ms | 3843 ms | — | 100.00% | — | 22 |
| phala | 4388 ms | 10337 ms | 4388 ms | — | 100.00% | — | 4 |
| cerebras | 5536 ms | 16023 ms | 5536 ms | — | 94.74% | — | 57 |
| zai | 7315 ms | 23500 ms | 7315 ms | — | 100.00% | — | 12 |
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.