OpenAI compatible API. Attested gateway. Public status.
DeepSeek: DeepSeek V4 Pro Performance
TrustedRouter performance signals and provider route posture for DeepSeek: DeepSeek V4 Pro.
1 URLbase_url migration
100smodels and routes
0prompt logs by default
deepseek/deepseek-v4-pro
Performance
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), throughput, and success rate for DeepSeek: DeepSeek V4 Pro — 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 |
|---|---|---|---|---|---|---|---|
| fireworks | 1104 ms | 2028 ms | 1013 ms | — | 60.00% | — | 65 |
| tinfoil | 1414 ms | 1684 ms | 1311 ms | — | 13.85% | — | 65 |
| novita | 1557 ms | 1685 ms | 1453 ms | — | 75.00% | — | 4 |
| siliconflow | 1690 ms | 2495 ms | 1591 ms | — | 60.00% | — | 45 |
| gmi | 3745 ms | 13133 ms | 3679 ms | — | 62.07% | — | 58 |
| deepseek | — | — | — | — | 0.00% | — | 164 |
| parasail | — | — | — | — | 0.00% | — | 5 |
Full provider & model leaderboard.
Provider diversity
14 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.