Qwen: Qwen3.8 27B Performance
Try Qwen3.8 27B on us. Starter credit covers your first requests, then one key reaches all 19 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 |
|---|---|---|---|---|---|---|
| regolo | 870 ms | 870 ms | — | 100.00% | — | 1 |
| cerebras | 1038 ms | 1221 ms | — | 100.00% | — | 5 |
| wandb | 1290 ms | 2198 ms | — | 100.00% | — | 2 |
| telnyx | 1342 ms | 1342 ms | — | 100.00% | — | 18 |
| akashml | 1678 ms | 1678 ms | — | 100.00% | — | 1 |
| pearl | 1862 ms | 3400 ms | — | 100.00% | — | 7 |
| atlas-cloud | 1958 ms | 1958 ms | — | 100.00% | — | 1 |
| crusoe | 2406 ms | 2406 ms | — | 100.00% | — | 5 |
| wafer | 2694 ms | 3971 ms | — | 100.00% | — | 2 |
| venice | 2834 ms | 3309 ms | — | 100.00% | — | 2 |
| deepinfra | 2874 ms | 2874 ms | — | 100.00% | — | 1 |
| chutes | 7019 ms | 8417 ms | — | 100.00% | — | 2 |
| lyceum | 20642 ms | 20642 ms | — | 100.00% | — | 1 |
| engy | — | — | — | 100.00% | 32 provider_error |
5 |
| novita | — | — | — | 100.00% | 2 provider_error |
2 |
Full provider & model leaderboard.
19 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.