OpenAI compatible API · Attested · Public status

DeepSeek: DeepSeek V4 Pro Performance

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

Verify gateway
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.

deepseek/deepseek-v4-pro

open weights Performance

All models

AI IQ IQ 115 #30 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), effective throughput, and success rate for DeepSeek: DeepSeek V4 Pro. 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.

Providerp50 TTFTp95 TTFTp50 TTFBEffective throughputUptimeConfig excludedAvailability samples
fireworks 2535 ms 2743 ms 2535 ms 100.00% 24
baseten 2717 ms 3642 ms 2717 ms 100.00% 18
novita 3169 ms 4025 ms 3169 ms 100.00% 5
siliconflow 3484 ms 6249 ms 3484 ms 100.00% 5
deepseek 2955 ms 3796 ms 2954 ms 97.67% 86
gmi 4540 ms 6553 ms 4540 ms 96.88% 32
parasail 3527 ms 12034 ms 3527 ms 80.00% 5
crusoe 2403 ms 3251 ms 2403 ms 76.92% 13
alibaba 0.00% 5
atlas-cloud 0.00% 2
digitalocean 0.00% 9
makora 0.00% 7 unsupported_route 22

Full provider & model leaderboard.

Provider diversity

26 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.