DeepSeek: DeepSeek V3.2 Performance
Compare measured TTFT, TTFB, throughput, uptime, and route health for DeepSeek V3.2 across TrustedRouter providers using metadata-only production probes.
deepseek/deepseek-v3.2
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), effective throughput, and success rate for DeepSeek: DeepSeek V3.2. 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 |
|---|---|---|---|---|---|---|---|
| siliconflow | 2453 ms | 3384 ms | 2453 ms | — | 100.00% | — | 2 |
| friendli | 2492 ms | 5782 ms | 2491 ms | — | 100.00% | — | 9 |
| digitalocean | 2712 ms | 2712 ms | 2712 ms | — | 100.00% | — | 1 |
| novita | 2803 ms | 2803 ms | 2803 ms | — | 100.00% | — | 1 |
| chutes | 3783 ms | 5951 ms | 3783 ms | — | 100.00% | — | 3 |
| deepinfra | — | — | — | — | 100.00% | — | 1 |
Full provider & model leaderboard.
15 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.