OpenAI compatible API. Attested gateway. Public status.

Z.ai: GLM 5.1 Performance

Name: Z.ai: GLM 5.1 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 5.1.

Verify gateway

1 URLbase_url migration

100smodels and routes

0prompt logs by default

`z-ai/glm-5.1`

open weights Performance

All models

AI IQ IQ 113 #19 public AI IQ rank for glm-5.1

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 5.1 — 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
friendli	4722 ms	14707 ms	4721 ms	—	100.00%	—	14
phala	4854 ms	31424 ms	4853 ms	—	80.00%	—	10
parasail	5620 ms	16967 ms	5619 ms	—	100.00%	—	8
zai	5755 ms	18369 ms	5754 ms	—	100.00%	—	16
crusoe	6129 ms	16883 ms	6129 ms	—	100.00%	—	16
venice	7084 ms	13273 ms	7083 ms	—	100.00%	—	21
fireworks	8100 ms	16683 ms	8100 ms	—	100.00%	—	17
baseten	8163 ms	16363 ms	8162 ms	—	91.67%	—	12
gmi	8951 ms	19476 ms	8950 ms	—	95.31%	—	64
wafer	9284 ms	23852 ms	9284 ms	—	100.00%	—	24

Full provider & model leaderboard.

Provider diversity

20 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.