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 117 #36 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
parasail 969 ms 1228 ms 100.00% 2
digitalocean 1177 ms 1277 ms 100.00% 2
wandb 1304 ms 1304 ms 100.00% 1
baseten 1452 ms 1452 ms 133 tok/s n=1 100.00% 1
gmi 1935 ms 4537 ms 100.00% 3
arcee 2798 ms 3437 ms 100.00% 5
venice 2981 ms 5234 ms 26 tok/s n=1 100.00% 2
deepseek 3878 ms 4413 ms 100.00% 5
siliconflow 4102 ms 4102 ms 30 tok/s n=1 100.00% 1
deepinfra 36 tok/s n=1 0
novita 37 tok/s n=1 0

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.