Get the latest tech news

Launch HN: IonRouter (YC W26) – High-throughput, low-cost inference


Zero-latency API auth and billing for distributed GPU inference.

None

Get the Android app

Or read this on Hacker News

Read more on:

Photo of throughput

throughput

Photo of w26

w26

Photo of cost inference

cost inference

Related news:

News photo

Nvidia's new open weights Nemotron 3 super combines three different architectures to beat gpt-oss and Qwen in throughput

News photo

Launch HN: Sentrial (YC W26) – Catch AI agent failures before your users do

News photo

Launch HN: Cardboard (YC W26) – Agentic video editor