OpenAI compatible API · Attested · Public status
DeepSeek: DeepSeek V3.2 Performance
TrustedRouter performance signals and provider route posture for DeepSeek: DeepSeek V3.2.
Onebase URL to migrate
100sof models and routes
Noneprompt logs by default
deepseek/deepseek-v3.2
open weights
Performance
AI IQ
IQ 104
#54 public AI IQ rank for deepseek-v3.2
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 DeepSeek: DeepSeek V3.2 — 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 |
|---|---|---|---|---|---|---|---|
| friendli | 4927 ms | 16728 ms | 4927 ms | — | 100.00% | — | 29 |
| atlas-cloud | 7841 ms | 18285 ms | 7841 ms | — | 100.00% | — | 8 |
| digitalocean | 8073 ms | 13011 ms | 8072 ms | — | 100.00% | — | 3 |
| deepinfra | 8497 ms | 8975 ms | 8496 ms | — | 66.67% | — | 3 |
| chutes | 8659 ms | 16822 ms | 8659 ms | — | 100.00% | — | 9 |
| novita | 10293 ms | 10442 ms | 10292 ms | — | 100.00% | — | 3 |
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.