OpenAI compatible API. Attested gateway. Public status.

DeepSeek: DeepSeek V4 Pro Performance

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

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

deepseek/deepseek-v4-pro

open weights Performance

All models

AI IQ IQ 109 #38 public AI IQ rank for deepseek-v4-pro
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 Pro — unsupported route and probe-configuration rows are separated from provider downtime, and no prompt or output content is stored.

Providerp50 TTFTp95 TTFTp50 TTFBThroughputUptimeConfig excludedSamples
baseten 1685 ms 1685 ms 1685 ms 87 tok/s 100.00% 109
deepseek 3899 ms 23231 ms 3899 ms 14 tok/s 100.00% 62
crusoe 4388 ms 21968 ms 4388 ms 91.67% 12
novita 4395 ms 4395 ms 4395 ms 100.00% 1
makora 4503 ms 13589 ms 4502 ms 95.83% 24
fireworks 5130 ms 14295 ms 5130 ms 27 tok/s 100.00% 42
gmi 6681 ms 21935 ms 6680 ms 100.00% 10
deepinfra 0.00% 2
phala 0.00% 6

Full provider & model leaderboard.

Provider diversity

22 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.