OpenAI compatible API. Attested gateway. Public status.
DeepSeek: DeepSeek V4 Flash Performance
TrustedRouter performance signals and provider route posture for DeepSeek: DeepSeek V4 Flash.
1 URLbase_url migration
100smodels and routes
0prompt logs by default
deepseek/deepseek-v4-flash
open weights
Performance
AI IQ
IQ 104
#38 public AI IQ rank for deepseek-v4-flash
View AI IQ profile
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), throughput, and success rate for DeepSeek: DeepSeek V4 Flash — 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 | Throughput | Uptime | Config excluded | Samples |
|---|---|---|---|---|---|---|---|
| siliconflow | 5181 ms | 19429 ms | 5181 ms | — | 100.00% | — | 37 |
| deepseek | 6637 ms | 18709 ms | 6636 ms | 9 tok/s | 100.00% | — | 121 |
| crusoe | 6831 ms | 14677 ms | 6830 ms | — | 100.00% | — | 14 |
| novita | 8623 ms | 23973 ms | 8623 ms | — | 100.00% | — | 7 |
| wafer | — | — | — | — | 0.00% | — | 19 |
Full provider & model leaderboard.
Provider diversity
12 routes.
More routes give the auto router more room to fail over around provider 429 and 5xx responses.
Streaming
Gateway overhead is measured separately.
Public status separates TLS/health overhead from full model latency so slow LLMs do not inflate the router metric.
Status
Metadata rollups.
Status samples store latency, outcome, provider, model, route, cost, and region metadata only.
View public status or inspect provider routes.