DeepSeek: DeepSeek V4 Pro 0423 Performance
Compare measured TTFT, throughput, uptime, and route health for DeepSeek V4 Pro 0423 across TrustedRouter providers using metadata-only production probes.
deepseek/deepseek-v4-pro
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), effective throughput, and success rate for DeepSeek: DeepSeek V4 Pro 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 |
|---|---|---|---|---|---|---|
| digitalocean | 1258 ms | 1341 ms | — | 100.00% | — | 3 |
| venice | 1481 ms | 1481 ms | — | 100.00% | — | 1 |
| parasail | 2084 ms | 4161 ms | — | 100.00% | — | 2 |
| deepseek | 2347 ms | 4371 ms | — | 100.00% | — | 9 |
| alibaba | 2765 ms | 2765 ms | — | 100.00% | — | 1 |
| io-net | 3794 ms | 3794 ms | — | 100.00% | — | 1 |
| gmi | 4026 ms | 4985 ms | — | 100.00% | — | 5 |
| arcee | 4859 ms | 5718 ms | — | 100.00% | — | 5 |
| novita | 5524 ms | 5524 ms | — | 100.00% | — | 1 |
| deepinfra | — | — | — | 100.00% | — | 2 |
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.