OpenAI compatible API · Attested · Public status

Z.ai: GLM 5.1 Performance

TrustedRouter performance signals and provider route posture for Z.ai: GLM 5.1.

Verify gateway
Onebase URL to migrate
100sof models and routes
Noneprompt logs by default

z-ai/glm-5.1

open weights Performance

All models

AI IQ IQ 113 #30 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.

Providerp50 TTFTp95 TTFTp50 TTFBThroughputUptimeConfig excludedSamples
atlas-cloud 3411 ms 5913 ms 3410 ms 100.00% 3
friendli 3554 ms 13806 ms 3554 ms 100.00% 31
zai 4552 ms 26289 ms 4551 ms 100.00% 23
wafer 5171 ms 17947 ms 5171 ms 97.44% 39
digitalocean 5239 ms 15770 ms 5239 ms 80.00% 15
fireworks 5609 ms 18105 ms 5609 ms 100.00% 33
crusoe 5663 ms 16859 ms 5662 ms 100.00% 15
gmi 6300 ms 20946 ms 6300 ms 100.00% 60
parasail 8323 ms 17146 ms 8323 ms 100.00% 7
baseten 9150 ms 17810 ms 9150 ms 100.00% 7
venice 9797 ms 19841 ms 9796 ms 100.00% 10
chutes 10071 ms 15477 ms 10070 ms 75.00% 12

Full provider & model leaderboard.

Provider diversity

23 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. New email and OAuth accounts include $0.10 in starter credit; wallet-only accounts start at $0.

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