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.
Onebase URL to migrate
100sof models and routes
Noneprompt logs by default
z-ai/glm-5.2
open weights
Performance
AI IQ
IQ 120
#14 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), throughput, and success rate for Z.ai: GLM 5.2 — 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 |
|---|---|---|---|---|---|---|---|
| venice | 2984 ms | 21453 ms | 2983 ms | — | 100.00% | — | 11 |
| morph | 3431 ms | 14925 ms | 3430 ms | — | 100.00% | — | 23 |
| deepinfra | 3514 ms | 3574 ms | 3514 ms | — | 100.00% | — | 3 |
| baseten | 4249 ms | 14737 ms | 4249 ms | — | 100.00% | — | 17 |
| siliconflow | 4274 ms | 11279 ms | 4274 ms | — | 100.00% | — | 23 |
| chutes | 4631 ms | 13241 ms | 4630 ms | — | 90.00% | — | 20 |
| tinfoil | 5119 ms | 20515 ms | 5119 ms | — | 88.89% | — | 27 |
| wafer | 5290 ms | 24294 ms | 5290 ms | — | 92.11% | — | 38 |
| together | 5665 ms | 18807 ms | 5665 ms | — | 94.12% | — | 17 |
| atlas-cloud | 5827 ms | 5827 ms | 5827 ms | — | 100.00% | — | 1 |
| fireworks | 5911 ms | 15049 ms | 5910 ms | — | 100.00% | — | 33 |
| parasail | 6431 ms | 13127 ms | 6431 ms | 78 tok/s | 100.00% | — | 34 |
| digitalocean | 6546 ms | 15961 ms | 6545 ms | — | 100.00% | — | 8 |
| friendli | 6740 ms | 12836 ms | 6740 ms | — | 100.00% | — | 21 |
| zai | 7313 ms | 19506 ms | 7313 ms | 20 tok/s | 100.00% | — | 17 |
| phala | 7453 ms | 26405 ms | 7453 ms | 28 tok/s | 97.37% | — | 38 |
| crusoe | 7483 ms | 14556 ms | 7483 ms | — | 100.00% | — | 8 |
| gmi | 7750 ms | 17117 ms | 7749 ms | — | 93.02% | — | 43 |
| makora | 8411 ms | 16168 ms | 8411 ms | — | 100.00% | — | 27 |
| novita | 8679 ms | 12747 ms | 8679 ms | — | 100.00% | — | 2 |
| inceptron | 12070 ms | 26754 ms | 12070 ms | — | 81.03% | 1 unsupported_route |
58 |
Full provider & model leaderboard.
Provider diversity
39 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.
View public status or inspect provider routes.