OpenAI compatible API · Attested · Public status
Z.ai: GLM 5V Turbo Performance
TrustedRouter performance signals and provider route posture for Z.ai: GLM 5V Turbo.
Onebase URL to migrate
100sof models and routes
Noneprompt logs by default
z-ai/glm-5v-turbo
open weights
Performance
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), throughput, and success rate for Z.ai: GLM 5V Turbo — 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 |
|---|---|---|---|---|---|---|---|
| zai | 4899 ms | 17912 ms | 4898 ms | — | 100.00% | — | 14 |
| siliconflow | 8237 ms | 22286 ms | 8237 ms | — | 100.00% | — | 7 |
| atlas-cloud | 8790 ms | 15277 ms | 8790 ms | — | 100.00% | — | 9 |
| venice | 9580 ms | 28421 ms | 9580 ms | — | 100.00% | — | 17 |
Full provider & model leaderboard.
Provider diversity
7 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.