OpenAI compatible API. Attested gateway. Public status.
Z.AI performance
Measured TTFT, TTFB, throughput, uptime, and sampled model routes for Z.AI.
1 URLbase_url migration
100smodels and routes
0prompt logs by default
zai
320 samples
Continuously sampled provider performance. TrustedRouter reports unsupported route and probe-configuration rows separately from provider downtime. Prompt and output content is not stored.
| p50 TTFT | 1489 ms |
|---|---|
| p95 TTFT | ms |
| p50 TTFB | ms |
| Throughput | 47 tok/s |
| Uptime | 91.87% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Throughput | Uptime | Config excluded | Samples |
|---|---|---|---|---|---|---|
| z-ai/glm-4.5v | 1014 ms | 1013 ms | — | 95.24% | — | 21 |
| z-ai/glm-4.6v | 1245 ms | 1203 ms | — | 100.00% | — | 32 |
| z-ai/glm-4.5 | 1326 ms | 1222 ms | — | 96.77% | — | 31 |
| z-ai/glm-4.5-air | 1328 ms | 1276 ms | — | 100.00% | — | 24 |
| z-ai/glm-5v-turbo | 1418 ms | 1349 ms | — | 100.00% | — | 29 |
| z-ai/glm-4.5-air:free | 1456 ms | 1353 ms | — | 100.00% | — | 16 |
| z-ai/glm-5-turbo | 1489 ms | 1386 ms | — | 90.00% | — | 30 |
| z-ai/glm-5.1 | 1905 ms | 1686 ms | 47 tok/s | 80.85% | — | 47 |
| z-ai/glm-4.7 | 1990 ms | 1982 ms | 60 tok/s | 100.00% | — | 22 |
| z-ai/glm-4.6 | 2121 ms | 2025 ms | — | 100.00% | — | 25 |
| z-ai/glm-5 | 2434 ms | 2341 ms | 6 tok/s | 100.00% | — | 31 |
| z-ai/glm-5.2 | — | — | — | 0.00% | — | 12 |