---
title: "Discussion on \"Streaming LLM Responses from FastAPI to Next.js with the OpenAI and Anthropic APIs\" | Hashnode"
description: "Discussion on \"Streaming LLM Responses from FastAPI to Next.js with the OpenAI and Anthropic APIs\". If you've built anything with LLMs recently, you know the problem: waiting three to eight seconds for a complete response before rendering anything feels broken. Users assume it's crashed. Streaming f"
url: "https://hashnode.com/posts/streaming-llm-responses-from-fastapi-to-next-js-with-the-openai-and-anthropic-apis/6a4dfe540248d9c0fe5412b3"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Streaming LLM Responses from FastAPI to Next.js with the OpenAI and Anthropic APIs](https://damianhodgkiss.hashnode.dev/streaming-llm-responses-from-fastapi-to-next-js-with-the-openai-and-anthropic-apis?utm_source=hashnode&utm_medium=feed)

If you've built anything with LLMs recently, you know the problem: waiting three to eight seconds for a complete response before rendering anything feels broken. Users assume it's crashed. Streaming f

Jul 8 · 12 min read · damianhodgkiss.hashnode.dev  
Read the article

-   [#nextjs](https://hashnode.com/tag/nextjs)
-   [#fastapi](https://hashnode.com/tag/fastapi)

## Written by

[Damian Hodgkiss](https://hashnode.com/@damianhodgkiss)

@damianhodgkiss

  
[View profile](https://hashnode.com/@damianhodgkiss)

🇦🇺 I build fast, scalable full-stack SaaS sites.

## Responses

Comments are turned off for this post.
