DeepSeek: DeepSeek V4 Flash Performance
TrustedRouter performance signals and provider route posture for DeepSeek: DeepSeek V4 Flash.
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. 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 |
|---|---|---|---|---|---|---|---|
| parasail | 705 ms | 1017 ms | 705 ms | 49 tok/s n=1 | 100.00% | — | 2 |
| deepinfra | 882 ms | 882 ms | 882 ms | 37 tok/s n=1 | 100.00% | — | 1 |
| morph | 1432 ms | 3638 ms | 1432 ms | 42 tok/s n=1 | 100.00% | — | 5 |
| fireworks | 1464 ms | 3670 ms | 1464 ms | 153 tok/s n=1 | 100.00% | — | 9 |
| makora | 1551 ms | 3278 ms | 1551 ms | 135 tok/s n=1 | 100.00% | — | 14 |
| crusoe | 1812 ms | 4051 ms | 1812 ms | 82 tok/s n=1 | 100.00% | — | 6 |
| deepseek | 1991 ms | 3810 ms | 1991 ms | 59 tok/s n=1 | 100.00% | — | 26 |
| siliconflow | 2209 ms | 2209 ms | 2209 ms | 32 tok/s n=1 | 100.00% | — | 1 |
| novita | 2953 ms | 2953 ms | 2952 ms | 67 tok/s n=1 | 100.00% | — | 1 |
| alibaba | 3404 ms | 3404 ms | 3404 ms | 82 tok/s n=1 | 100.00% | — | 1 |
| digitalocean | 3423 ms | 5163 ms | 3423 ms | 20 tok/s n=1 | 100.00% | — | 3 |
| atlas-cloud | — | — | — | 75 tok/s n=1 | — | — | 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.