API responds with 500 error when calling OpenAI from Next.js

Question

I'm trying to use the OpenAI API to analyze a physics question in my Next.js project. However, when I send a POST request to my API, I receive a 500 Internal Server Error. I've checked the code and confirmed that my API key is valid, but I can't resolve this issue. Below is the code I'm using: Code:

import { NextResponse } from 'next/server';

export async function POST(req) {
  const { question } = await req.json();
  const result = await analyzeQuestion(question);
  return NextResponse.json(result);
}

async function analyzeQuestion(question) {
  const response = await fetch('https://api.openai.com/v1/chat/completions', {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      'Authorization': 'Bearer sk-xxxxxx', // Replace with your API key
    },
    body: JSON.stringify({
      model: 'gpt-3.5-turbo',
      messages: [
        { role: 'system', content: 'You are an educational assistant' },
        { role: 'user', content: question },
      ],
      temperature: 0.3,
      max_tokens: 500,
    }),
  });
  const data = await response.json();
  return data.choices[0]?.message.content || {};
}

Error Received:

Failed to load resource: the server responded with a status of 500 (Internal Server Error)

What I have tried: I have checked the API key, tried sending requests with different parameters, and made sure there are no syntax errors in my code. I've also tried restarting the server and checking the logs, but the issue still persists.

Help Request: Can anyone help me figure out the cause of this issue and how to fix the 500 error?

Your post contains several indicators that ChatGPT or another LLM was used to generate it. For a variety of reasons, the use of such generative AI tools is strictly disallowed on Stack Overflow. Please edit your question to remove and replace content that was generated using these tools. — esqew
– esqew, Commented Apr 10 at 21:24

omargpax · Accepted Answer · 2025-04-10 23:22:07Z

If you are using the free trial version of OpenAI, you may encounter limitations that could cause a 500 Internal Server Error.

You could try ‘@ai-sdk/openai’ is not available in the free tier(you might need to configure the provider correctly).

import { openai } from "@ai-sdk/openai";

async function sendMessage(message: string) {
  try {
    const { text } = await generateText({
      model: openai("gpt-4-turbo"), // Uses the GPT-4 Turbo model
      system: "You are an educational assistant",
      prompt: message,
    });
    return text;
  } catch (error) {
    console.error("Error generating text:", error);
    throw new Error("response could not be generated");
  }
}

Or maybe add proper error handling:

async function analyzeQuestion(question) {
  try {
    const response = await fetch('https://api.openai.com/v1/chat/completions', {
      method: 'POST',
      headers: {
        'Content-Type': 'application/json',
        'Authorization': `Bearer ${process.env.OPENAI_API_KEY}`, // Better to use environment variables
      },
      body: JSON.stringify({
        model: 'gpt-3.5-turbo',
        messages: [
          { role: 'system', content: 'You are an educational assistant' },
          { role: 'user', content: question },
        ],
        temperature: 0.3,
        max_tokens: 500,
      }),
    });

    if (!response.ok) {
      const errorData = await response.json();
      throw new Error(errorData.error?.message || 'Failed to fetch from OpenAI');
    }

    const data = await response.json();
    return data.choices[0]?.message?.content || 'No response from AI';
  } catch (error) {
    console.error('OpenAI API error:', error);
    return { error: error.message };
  }
}

Collectives™ on Stack Overflow

API responds with 500 error when calling OpenAI from Next.js

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related