Qwen: Qwen3.5 397B A17B Performance
TrustedRouter performance signals and provider route posture for Qwen: Qwen3.5 397B A17B.
qwen/qwen3.5-397b-a17b
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), effective throughput, and success rate for Qwen: Qwen3.5 397B A17B. 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 |
|---|---|---|---|---|---|---|---|
| deepinfra | 1338 ms | 1673 ms | 1338 ms | — | 100.00% | — | 2 |
| digitalocean | 1374 ms | 1640 ms | 1374 ms | — | 100.00% | — | 6 |
| venice | 2587 ms | 4429 ms | 2587 ms | — | 100.00% | — | 8 |
| novita | 4010 ms | 4080 ms | 4010 ms | — | 100.00% | — | 2 |
| morph | 2289 ms | 11779 ms | 2289 ms | — | 88.89% | — | 9 |
| chutes | 2475 ms | 4164 ms | 2475 ms | — | 83.33% | — | 6 |
| alibaba | — | — | — | — | 0.00% | — | 2 |
Full provider & model leaderboard.
16 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.