DeepSeek: DeepSeek V4 Flash 0423 Performance
Try DeepSeek V4 Flash 0423 on us. Starter credit covers your first requests, then one key reaches all 10 provider routes with automatic failover.
deepseek/deepseek-v4-flash
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), effective throughput, and success rate for DeepSeek: DeepSeek V4 Flash 0423. 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 |
|---|---|---|---|---|---|---|
| mancer | 1188 ms | 3136 ms | 46 tok/s n=1 | 100.00% | — | 6 |
| deepseek | 1198 ms | 2458 ms | 152 tok/s n=1 | 100.00% | 1 provider_error |
6 |
| digitalocean | 1217 ms | 1217 ms | — | 100.00% | — | 1 |
| parasail | 1626 ms | 1626 ms | — | 100.00% | — | 1 |
| streamlake | 1858 ms | 1858 ms | — | 100.00% | — | 1 |
| morph | 2291 ms | 11862 ms | — | 100.00% | — | 5 |
Full provider & model leaderboard.
10 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.