OpenAI compatible API. Attested gateway. Public status.

Z.ai: GLM 5 Performance

Name: Z.ai: GLM 5 TrustedRouter performance measurements
Creator: TrustedRouter
License: https://www.apache.org/licenses/LICENSE-2.0

TrustedRouter performance signals and provider route posture for Z.ai: GLM 5.

Verify gateway

1 URLbase_url migration

100smodels and routes

0prompt logs by default

`z-ai/glm-5`

open weights Performance

All models

AI IQ IQ 107 #34 public AI IQ rank for glm-5

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 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
zai	4705 ms	16261 ms	4704 ms	—	100.00%	—	21
siliconflow	5129 ms	19914 ms	5128 ms	—	94.59%	—	37
venice	5234 ms	17002 ms	5234 ms	—	100.00%	—	30
gmi	6613 ms	35532 ms	6613 ms	—	55.93%	—	59
phala	7047 ms	21753 ms	7046 ms	—	90.00%	—	20
baseten	8012 ms	26783 ms	8011 ms	—	92.31%	—	13

Full provider & model leaderboard.

Provider diversity

13 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.