Forem

gauravdagde profile picture

gauravdagde

Building Preto.ai — LLM cost optimization for engineering teams. Writing about AI infrastructure, LLM proxies, and keeping your OpenAI bill under control.

Location Pune, India Joined Joined on  Personal website https://preto.ai github website

Education

University of Pune

Work

Founder / CTO at Preto.ai

LLM Gateway vs LLM Proxy vs LLM Router: What's the Difference?
Cover image for LLM Gateway vs LLM Proxy vs LLM Router: What's the Difference?

LLM Gateway vs LLM Proxy vs LLM Router: What's the Difference?

Comments
4 min read

Want to connect with gauravdagde?

Create an account to connect with gauravdagde. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
LLM Semantic Caching: The 95% Hit Rate Myth (and What Production Data Actually Shows)
Cover image for LLM Semantic Caching: The 95% Hit Rate Myth (and What Production Data Actually Shows)

LLM Semantic Caching: The 95% Hit Rate Myth (and What Production Data Actually Shows)

2
Comments 1
7 min read
We built an LLM proxy that adds 47ms of latency. Here's every millisecond accounted for.
Cover image for We built an LLM proxy that adds 47ms of latency. Here's every millisecond accounted for.

We built an LLM proxy that adds 47ms of latency. Here's every millisecond accounted for.

1
Comments
8 min read
We evaluated Go, Rust, and Python for our LLM proxy. Go won - and not for the reason you'd expect.
Cover image for We evaluated Go, Rust, and Python for our LLM proxy. Go won - and not for the reason you'd expect.

We evaluated Go, Rust, and Python for our LLM proxy. Go won - and not for the reason you'd expect.

1
Comments
6 min read
How to integrate coroot-pg-agent with prometheus

How to integrate coroot-pg-agent with prometheus

1
Comments 1
4 min read
loading...