---
title: "Comment by Kartik N V J K on \"Deploying AI Workflows on Cloud Run: Latency, Cold Starts, and Scaling\" | Hashnode"
description: "min_instances=3 turning into 40% of the bill is the kind of fix that looks free on launch day and shows up a quarter later. Splitting cold start into provisioni"
url: "https://hashnode.com/posts/deploying-ai-workflows-on-cloud-run-latency-cold-starts-and-scaling/6ac7e695eed20210cedb42bf/comment/6ac93d61e04056046d05ddf5"
---

[Discussion](https://hashnode.com/posts/deploying-ai-workflows-on-cloud-run-latency-cold-starts-and-scaling/6ac7e695eed20210cedb42bf)

Comment [Deploying AI Workflows on Cloud Run: Latency, Cold Starts, and Scaling](https://hashnode.com/posts/deploying-ai-workflows-on-cloud-run-latency-cold-starts-and-scaling/6ac7e695eed20210cedb42bf)

[Kartik N V J K](https://hashnode.com/@kartik-nvj)

[Oct 9](https://hashnode.com/posts/deploying-ai-workflows-on-cloud-run-latency-cold-starts-and-scaling/6ac7e695eed20210cedb42bf/comment/6ac93d61e04056046d05ddf5)

min\_instances=3 turning into 40% of the bill is the kind of fix that looks free on launch day and shows up a quarter later. Splitting cold start into provisioning, app init, and the first LLM call is the useful move, since the 2-5s of SDK plus pool warmup is the part you can actually attack. Did the warming endpoint alone get you there, or did you also lazy-load the heavier imports?
