OpenAI compatible API · Attested · Public status
Qwen: Qwen3.5 397B A17B Performance
TrustedRouter performance signals and provider route posture for Qwen: Qwen3.5 397B A17B.
Onebase URL to migrate
100sof models and routes
Noneprompt logs by default
qwen/qwen3.5-397b-a17b
open weights
Performance
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), throughput, and success rate for Qwen: Qwen3.5 397B A17B — 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 | Throughput | Uptime | Config excluded | Samples |
|---|---|---|---|---|---|---|---|
| digitalocean | 1378 ms | 4044 ms | 1378 ms | — | 75.00% | — | 8 |
| atlas-cloud | 1657 ms | 1657 ms | 1657 ms | — | 100.00% | — | 1 |
| novita | 2219 ms | 2838 ms | 2218 ms | — | 100.00% | — | 3 |
| chutes | 3649 ms | 15857 ms | 3649 ms | — | 100.00% | — | 14 |
| venice | 5545 ms | 20582 ms | 5545 ms | — | 100.00% | — | 16 |
| deepinfra | 6017 ms | 15980 ms | 6017 ms | — | 100.00% | — | 4 |
| morph | 7080 ms | 15222 ms | 7080 ms | — | 100.00% | — | 24 |
Full provider & model leaderboard.
Provider diversity
15 routes.
More routes give the auto router more room to fail over around provider 429 and 5xx responses.
Streaming
Gateway overhead is measured separately.
Public status separates TLS/health overhead from full model latency so slow LLMs do not inflate the router metric.
Status
Metadata rollups.
Status samples store latency, outcome, provider, model, route, cost, and region metadata only.
View public status or inspect provider routes.