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
Noneprompt logs by default

deepseek/deepseek-v4-pro

open weights Performance

All models

AI IQ IQ 114 #27 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
parasail 3234 ms 9011 ms 3234 ms 66.67% 3
fireworks 4005 ms 16116 ms 4005 ms 100.00% 32
atlas-cloud 4244 ms 11311 ms 4244 ms 100.00% 2
deepseek 4628 ms 16249 ms 4628 ms 97.92% 96
digitalocean 4695 ms 15253 ms 4695 ms 92.31% 13
makora 5177 ms 20558 ms 5177 ms 86.36% 22
gmi 5547 ms 13454 ms 5547 ms 100.00% 41
deepinfra 5843 ms 5843 ms 5843 ms 100.00% 1
siliconflow 6645 ms 6844 ms 6644 ms 100.00% 4
baseten 8098 ms 17007 ms 8098 ms 86 tok/s 100.00% 12
crusoe 11139 ms 16639 ms 11139 ms 100.00% 11

Full provider & model leaderboard.

Provider diversity

25 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.