OpenAI compatible API · Attested · Public status

DeepSeek: DeepSeek V4 Pro 0423 Performance

Compare measured TTFT, throughput, uptime, and route health for DeepSeek V4 Pro 0423 across TrustedRouter providers using metadata-only production probes.

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 114 #47 public AI IQ rank for deepseek-v4-pro
View AI IQ profile

Measured performance

Continuously sampled p50/p95 time-to-first-token (TTFT), effective throughput, and success rate for DeepSeek: DeepSeek V4 Pro 0423. 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 TTFTEffective throughputUptimeConfig excludedAvailability samples
digitalocean 1341 ms 3722 ms 100.00% 5
venice 1481 ms 2423 ms 100.00% 2
deepseek 1585 ms 4371 ms 100.00% 4
parasail 2084 ms 4161 ms 66.67% 3
siliconflow 2268 ms 2268 ms 100.00% 1
alibaba 2765 ms 2765 ms 100.00% 1
gmi 2878 ms 4985 ms 100.00% 6
io-net 3384 ms 3794 ms 100.00% 2
baseten 3698 ms 3698 ms 100.00% 1
arcee 5088 ms 6263 ms 100.00% 3
featherless 6961 ms 7534 ms 100.00% 2
deepinfra 100.00% 2

Full provider & model leaderboard.

Provider diversity

16 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 to access your TrustedRouter workspace.

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