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.
z-ai/glm-5.3-flash
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.
| Provider | p50 TTFT | p95 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| together | 577 ms | 3302 ms | — | 100.00% | — | 2 |
| telnyx | 1327 ms | 1327 ms | — | 100.00% | — | 3 |
| sail-research | 1515 ms | 15817 ms | — | 80.00% | — | 5 |
| friendli | 1621 ms | 3782 ms | — | 100.00% | — | 6 |
| fireworks | 1658 ms | 1658 ms | — | 100.00% | — | 1 |
| tinfoil | 1734 ms | 2994 ms | — | 83.33% | — | 6 |
| wafer | 1851 ms | 4061 ms | — | 100.00% | — | 9 |
| featherless | 2424 ms | 2792 ms | — | 100.00% | — | 2 |
| pearl | 2461 ms | 5014 ms | — | 100.00% | — | 7 |
| makora | 2498 ms | 4064 ms | — | 100.00% | 1 unsupported_route |
2 |
| near-ai | 3555 ms | 3555 ms | — | 3.85% | — | 26 |
| arcee | 3569 ms | 6524 ms | — | 100.00% | — | 3 |
| zai | 3569 ms | 3569 ms | — | 100.00% | — | 19 |
| parasail | 3594 ms | 3773 ms | — | 100.00% | — | 3 |
| engy | 4413 ms | 4413 ms | — | 100.00% | — | 1 |
| siliconflow | 4589 ms | 4589 ms | — | 100.00% | — | 1 |
| io-net | 8004 ms | 8004 ms | — | 100.00% | — | 1 |
| deepinfra | 8086 ms | 8086 ms | — | 100.00% | — | 1 |
| nvidia-nim | — | — | — | 0.00% | — | 3 |
| phala | — | — | — | 0.00% | — | 2 |
Full provider & model leaderboard.
26 routes.
More routes give the auto router more room to fail over around provider 429 and 5xx responses.
Gateway overhead is measured separately.
Public status separates TLS/health overhead from full model latency so slow LLMs do not inflate the router metric.
Metadata rollups.
Status samples store latency, outcome, provider, model, route, cost, and region metadata only.
View public status or inspect provider routes.