DeepSeek: DeepSeek V4.1 Flash 1017 Performance
Try DeepSeek V4.1 Flash 1017 on us. Starter credit covers your first requests, then one key reaches all 16 provider routes with automatic failover.
deepseek/deepseek-v4.1-flash-1017
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), effective throughput, and success rate for DeepSeek: DeepSeek V4.1 Flash 1017. 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 |
|---|---|---|---|---|---|---|
| makora | 862 ms | 2211 ms | — | 100.00% | — | 2 |
| nebius | 1007 ms | 1266 ms | — | 100.00% | — | 2 |
| sail-research | 1060 ms | 2002 ms | — | 100.00% | — | 4 |
| lyceum | 1196 ms | 1616 ms | — | 100.00% | — | 4 |
| tinfoil | 1272 ms | 2728 ms | — | 100.00% | — | 8 |
| engy | 1445 ms | 1735 ms | — | 100.00% | — | 5 |
| pearl | 1554 ms | 3056 ms | — | 100.00% | — | 5 |
| arcee | 2493 ms | 2941 ms | — | 100.00% | — | 6 |
| morph | 3731 ms | 8306 ms | — | 100.00% | — | 6 |
Full provider & model leaderboard.
16 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.