调用OpenAI GPT-3 API报错：Invalid URL (POST /v1/chat/completions)求助

你遇到的问题核心是模型与API接口不匹配，下面是两种可行的解决办法：

方法一：切换为聊天模型（推荐） #

createChatCompletion（或v4版本的chat.completions.create）是专门给GPT-3.5/4系列聊天模型设计的接口，必须搭配gpt-3.5-turbo这类模型，同时参数要换成messages而非prompt：

如果你用的是openai v4版本： #

const { OpenAI } = require("openai");

const openai = new OpenAI({
  apiKey: 'MY KEY'
});

async function start() {
  const response = await openai.chat.completions.create({
    model: "gpt-3.5-turbo",
    messages: [
      { role: "user", content: "Write a 90 word essay about Family Guy" }
    ],
    temperature: 0,
    max_tokens: 1000
  });

  console.log(response.choices[0].message.content);
}

start();

如果你用的是openai v3版本： #

const { Configuration, OpenAIApi } = require("openai");

const configuration = new Configuration({
  apiKey: 'MY KEY'
});

const openai = new OpenAIApi(configuration);

async function start() {
  const response = await openai.createChatCompletion({
    model: "gpt-3.5-turbo",
    messages: [
      { role: "user", content: "Write a 90 word essay about Family Guy" }
    ],
    temperature: 0,
    max_tokens: 1000
  });

  console.log(response.data.choices[0].message.content);
}

start();

方法二：继续使用text-davinci-003模型 #

如果不想更换模型，就改用文本补全接口createCompletion，这才是text-davinci-003对应的官方接口：

const { Configuration, OpenAIApi } = require("openai");

const configuration = new Configuration({
  apiKey: 'MY KEY'
});

const openai = new OpenAIApi(configuration);

async function start() {
  const response = await openai.createCompletion({
    model: "text-davinci-003",
    prompt: "Write a 90 word essay about Family Guy",
    temperature: 0,
    max_tokens: 1000
  });

  console.log(response.data.choices[0].text);
}

start();

错误原因说明 #

• text-davinci-003属于文本补全模型，对应的API端点是/v1/completions；而你调用的createChatCompletion是聊天模型专属接口，对应/v1/chat/completions，两者完全不兼容，因此触发URL无效错误。
• 额外注意openai库的版本差异：v4版本简化了调用逻辑，移除了Configuration和OpenAIApi类，直接通过OpenAI实例调用方法。

内容的提问来源于stack exchange，提问作者Das CO