OpenAI compatible API · Attested · Public status
Qwen: Qwen3.6 35B A3B Performance
TrustedRouter performance signals and provider route posture for Qwen: Qwen3.6 35B A3B.
Onebase URL to migrate
100sof models and routes
Noneprompt logs by default
qwen/qwen3.6-35b-a3b
open weights
Performance
AI IQ
IQ 96
#68 public AI IQ rank for qwen3.6-35b-a3b
View AI IQ profile
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), throughput, and success rate for Qwen: Qwen3.6 35B A3B — 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 |
|---|---|---|---|---|---|---|---|
| atlas-cloud | 1531 ms | 9756 ms | 1531 ms | — | 66.67% | — | 3 |
| deepinfra | 2760 ms | 2760 ms | 2760 ms | — | 100.00% | 3 unsupported_route |
1 |
| siliconflow | 7588 ms | 10378 ms | 7588 ms | — | 100.00% | — | 2 |
| novita | 9705 ms | 13362 ms | 9705 ms | — | 100.00% | — | 2 |
| parasail | — | — | — | — | 0.00% | 5 probe_config_error |
1 |
Full provider & model leaderboard.
Provider diversity
12 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.