DeepSeek: DeepSeek V3.2 Performance
Compare measured TTFT, 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), 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 | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| friendli | 1063 ms | 3113 ms | — | 100.00% | — | 4 |
| sambanova | 1741 ms | 2042 ms | — | 100.00% | — | 2 |
| deepinfra | 2025 ms | 2025 ms | — | 100.00% | — | 1 |
| digitalocean | 3585 ms | 4122 ms | — | 100.00% | — | 2 |
| atlas-cloud | 4438 ms | 4438 ms | — | 100.00% | — | 1 |
| chutes | 9128 ms | 9639 ms | — | 100.00% | — | 3 |
Full provider & model leaderboard.
9 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.