DeepSeek: DeepSeek V3.1 Terminus Performance
TrustedRouter performance signals and provider route posture for DeepSeek: DeepSeek V3.1 Terminus.
deepseek/deepseek-v3.1-terminus
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), effective throughput, and success rate for DeepSeek: DeepSeek V3.1 Terminus. 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 |
|---|---|---|---|---|---|---|---|
| atlas-cloud | 2306 ms | 3622 ms | 2305 ms | — | 100.00% | — | 4 |
| siliconflow | 2596 ms | 2596 ms | 2595 ms | — | 100.00% | 1 unsupported_route |
1 |
| novita | 2783 ms | 2783 ms | 2782 ms | — | 100.00% | — | 1 |
| deepinfra | 3346 ms | 7381 ms | 3345 ms | — | 100.00% | — | 3 |
Full provider & model leaderboard.
7 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.