OpenAI compatible API · Attested · Public status

Z.ai: GLM 5.3 Flash Performance

Compare measured TTFT, throughput, uptime, and route health for Z.ai: GLM 5.3 Flash across TrustedRouter providers using metadata-only production probes.

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

z-ai/glm-5.3-flash

open weights Performance

All models

AI IQ IQ 121 #24 public AI IQ rank for GLM-5.3-Flash
View AI IQ profile

Measured performance

Continuously sampled p50/p95 time-to-first-token (TTFT), effective throughput, and success rate for Z.ai: GLM 5.3 Flash. 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 TTFTEffective throughputUptimeConfig excludedAvailability samples
wafer 1281 ms 12698 ms 100.00% 10
pearl 3128 ms 3755 ms 91.67% 12
zai 3147 ms 7240 ms 100.00% 11
baseten 863 ms 863 ms 100.00% 1
fireworks 944 ms 944 ms 100.00% 1
telnyx 1234 ms 2583 ms 100.00% 4
engy 1248 ms 2272 ms 100.00% 5
nebius 1802 ms 40643 ms 100.00% 4
friendli 1928 ms 2468 ms 100.00% 5
featherless 1960 ms 6035 ms 100.00% 2
tinfoil 3012 ms 4314 ms 100.00% 9
makora 3657 ms 4849 ms 100.00% 1 unsupported_route 5
arcee 4421 ms 16998 ms 100.00% 6
parasail 4428 ms 4428 ms 100.00% 1
phala 0.00% 11

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.

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.