ECE TSG AI API Gateway

Requests

—

Input tokens

—

total, incl. cached

Effective input

—

billed / uncached

Cache hit

—

Output tokens

—

generated

Avg latency

—

model processing

Avg wait · 30 min

—

queue time

Queue position

—

new request

Last 24 hours

avg wait ≤ 5 s 5–10 s > 10 s per 30 min · hover for details

Loading…

Token usage

Input Output Cache hit per 15 min · last 24 h · hover for details

0

Loading…

Models

liveness, live queue and performance · last 24 h

Loading status…