---
title: "Serve the Model Over HTTP"
description: "Put a loaded LLM behind an HTTP endpoint with FastAPI and uvicorn, call it from your laptop, stream tokens over HTTP, and see where a simple server stops."
canonical_url: "https://fanout.sh/inference-eng/curriculum/01-05"
md_url: "https://fanout.sh/inference-eng/curriculum/01-05.md"
access: "public"
---

# Serve the Model Over HTTP

Put a loaded LLM behind an HTTP endpoint with FastAPI and uvicorn, call it from your laptop, stream tokens over HTTP, and see where a simple server stops.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md