OpenAI compatible API · Attested · Public status

Z.ai: GLM 5.2 Performance

TrustedRouter performance signals and provider route posture for Z.ai: GLM 5.2.

Verify gateway
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.

z-ai/glm-5.2

open weights Performance

All models

AI IQ IQ 120 #16 public AI IQ rank for glm-5.2
View AI IQ profile

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 5.2. 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.

Providerp50 TTFTp95 TTFTp50 TTFBEffective throughputUptimeConfig excludedAvailability samples
fireworks 1344 ms 2168 ms 1344 ms 100.00% 4
friendli 1425 ms 1553 ms 1425 ms 100.00% 3
baseten 1675 ms 1891 ms 1675 ms 100.00% 2
parasail 1835 ms 1835 ms 1835 ms 100.00% 1
gmi 1846 ms 2780 ms 1846 ms 100.00% 3
makora 2202 ms 2233 ms 2201 ms 100.00% 5
novita 2436 ms 2436 ms 2436 ms 100.00% 1
phala 2622 ms 38091 ms 2622 ms 100.00% 10
wafer 2155 ms 5501 ms 2155 ms 50.00% 4
tinfoil 7785 ms 21050 ms 7784 ms 50.00% 4
alibaba 0.00% 1
chutes 0.00% 1
cloudflare-workers-ai 0.00% 1
digitalocean 0.00% 1
engy 0.00% 11
inceptron 0.00% 10
morph 0.00% 3
telnyx 0.00% 3
zero-g 0.00% 5

Full provider & model leaderboard.

Provider diversity

45 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.

Workspace access

Sign in

Choose a sign in method to access your TrustedRouter workspace.

By signing in you agree to the terms of service and privacy policy.