OpenAI compatible API · Attested · Public status

DeepSeek: DeepSeek V4 Flash Performance

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

Verify gateway
Onebase URL to migrate
100sof models and routes
Noneprompt logs by default

deepseek/deepseek-v4-flash

open weights Performance

All models

AI IQ IQ 109 #42 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
makora 2079 ms 14869 ms 2079 ms 100.00% 16
crusoe 2349 ms 16217 ms 2349 ms 100.00% 9
deepinfra 3114 ms 14043 ms 3113 ms 100.00% 4
digitalocean 3298 ms 12769 ms 3298 ms 100.00% 8
parasail 4260 ms 17012 ms 4260 ms 100.00% 6
novita 5498 ms 5498 ms 5498 ms 100.00% 1
deepseek 5762 ms 16724 ms 5762 ms 98.95% 95
siliconflow 5967 ms 13837 ms 5967 ms 100.00% 8
morph 8663 ms 15184 ms 8663 ms 100.00% 17
atlas-cloud 9047 ms 9047 ms 9047 ms 100.00% 1

Full provider & model leaderboard.

Provider diversity

19 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.

Workspace access

Sign in

Choose a sign in method. New email and OAuth accounts include $0.10 in starter credit; wallet-only accounts start at $0.

By signing in you agree to the terms of service and privacy policy.