Qwen: Qwen3.5 397B A17B Performance
Try Qwen3.5 397B A17B on us. Starter credit covers your first requests, then one key reaches all 11 provider routes with automatic failover.
qwen/qwen3.5-397b-a17b
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), 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 | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| scaleway | 816 ms | 1200 ms | — | 100.00% | — | 2 |
| parasail | 925 ms | 1605 ms | — | 100.00% | — | 2 |
| streamlake | 1751 ms | 1751 ms | — | 100.00% | — | 1 |
| venice | 2286 ms | 2286 ms | — | 100.00% | — | 1 |
| alibaba | 2687 ms | 2687 ms | — | 100.00% | — | 1 |
| novita | 3095 ms | 3095 ms | — | 100.00% | — | 1 |
| featherless | 3870 ms | 3870 ms | — | 100.00% | — | 1 |
| chutes | 6255 ms | 6705 ms | — | 100.00% | — | 3 |
Full provider & model leaderboard.
11 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.