GLM 5.2 Fast on Fireworks Performance
TrustedRouter performance signals and provider route posture for GLM 5.2 Fast on Fireworks.
z-ai/glm-5.2-fast
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), effective throughput, and success rate for GLM 5.2 Fast on Fireworks. 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 | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|---|
| fireworks | 730 ms | 3060 ms | 729 ms | 55 tok/s n=1 | 100.00% | — | 5 |
| wafer | 2788 ms | 4812 ms | 2788 ms | 219 tok/s n=1 | 100.00% | — | 13 |
| baseten | 3111 ms | 5323 ms | 3111 ms | 64 tok/s n=1 | 100.00% | — | 6 |
Full provider & model leaderboard.
6 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.