DeepSeek: DeepSeek V4 Flash 0423 Performance
Compare measured TTFT, TTFB, throughput, uptime, and route health for DeepSeek V4 Flash 0423 across TrustedRouter providers using metadata-only production probes.
deepseek/deepseek-v4-flash
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), 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 | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|---|
| makora | 1077 ms | 3175 ms | 1077 ms | 106 tok/s n=2 | 100.00% | 4 probe_config_error |
9 |
| crusoe | 1461 ms | 3552 ms | 1460 ms | 35 tok/s n=2 | 100.00% | — | 4 |
| parasail | 1575 ms | 20850 ms | 1575 ms | 81 tok/s n=2 | 100.00% | — | 3 |
| morph | 1646 ms | 22057 ms | 1646 ms | 65 tok/s n=2 | 100.00% | — | 7 |
| deepseek | 1787 ms | 3802 ms | 1787 ms | 90 tok/s n=1 | 100.00% | — | 19 |
| siliconflow | 2236 ms | 2236 ms | 2236 ms | 72 tok/s n=2 | 100.00% | — | 1 |
| atlas-cloud | 2887 ms | 2887 ms | 2887 ms | 74 tok/s n=2 | 100.00% | — | 1 |
| fireworks | 4038 ms | 4611 ms | 4037 ms | 56 tok/s n=2 | 100.00% | — | 3 |
| digitalocean | 4449 ms | 4541 ms | 4449 ms | 14 tok/s n=2 | 100.00% | — | 2 |
| alibaba | — | — | — | 69 tok/s n=2 | — | — | 0 |
| deepinfra | — | — | — | 62 tok/s n=2 | — | — | 0 |
| novita | — | — | — | 64 tok/s n=2 | — | — | 0 |
Full provider & model leaderboard.
22 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.