OpenAI compatible API. Attested gateway. Public status.

DeepSeek: DeepSeek V4 Flash Performance

TrustedRouter performance signals and provider route posture for DeepSeek: DeepSeek V4 Flash.

Verify gateway
1 URLbase_url migration
100smodels and routes
0prompt logs by default

deepseek/deepseek-v4-flash

open weights Performance

All models

AI IQ IQ 105 #46 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.

Providerp50 TTFTp95 TTFTp50 TTFBThroughputUptimeConfig excludedSamples
parasail 3329 ms 20061 ms 3329 ms 100.00% 14
makora 3716 ms 15677 ms 3716 ms 100.00% 30
deepseek 4264 ms 15081 ms 4263 ms 100.00% 38
novita 5288 ms 13810 ms 5288 ms 100.00% 6
crusoe 7262 ms 8041 ms 7262 ms 100.00% 3
deepinfra 0.00% 1 unsupported_route 3
phala 0.00% 1 unsupported_route 4
gmi 0.00% 1 provider_error 3

Full provider & model leaderboard.

Provider diversity

18 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.

Sign in

Choose a sign in method.