Qwen: Qwen3.8 27B Performance
Try Qwen3.8 27B on us. Starter credit covers your first requests, then one key reaches all 20 provider routes with automatic failover.
qwen/qwen3.8-27b
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), effective throughput, and success rate for Qwen: Qwen3.8 27B. 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 |
|---|---|---|---|---|---|---|
| engy | 630 ms | 1515 ms | — | 100.00% | 3 insufficient_quota |
2 |
| muna | 696 ms | 2483 ms | 126 tok/s n=1 | 100.00% | — | 4 |
| akashml | 830 ms | 830 ms | — | 100.00% | — | 1 |
| cerebras | 1083 ms | 2825 ms | — | 100.00% | — | 7 |
| novita | 1147 ms | 1147 ms | — | 100.00% | — | 1 |
| regolo | 1459 ms | 1459 ms | — | 100.00% | — | 1 |
| wafer | 1533 ms | 2694 ms | — | 100.00% | — | 4 |
| pearl | 1866 ms | 3846 ms | — | 100.00% | — | 4 |
| wandb | 1866 ms | 3265 ms | — | 100.00% | — | 3 |
| io-net | 2331 ms | 2331 ms | — | 100.00% | — | 1 |
| venice | 2834 ms | 2834 ms | — | 100.00% | — | 1 |
| chutes | 6769 ms | 13223 ms | — | 100.00% | — | 4 |
Full provider & model leaderboard.
20 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.