Vercel站点调用OpenAI text-curie-001接口返回500错误求助

问题背景 #

• 部署于Vercel的故事生成站点（访问地址：https://original-story-maker.vercel.app/）调用OpenAI text-curie-001模型接口时返回500服务器错误，当前账号使用OpenAI免费额度
• 原接口请求代码如下：

import { Configuration, OpenAIApi } from "openai";

const configuration = new Configuration({
  apiKey: process.env.OPENAI_API_KEY,
});
const openai = new OpenAIApi(configuration);

export default async function (req, res) {
  const completion = await openai.createCompletion("text-curie-001", {
    // prompt: generatePrompt(req.body.animal),
    prompt: "Write a story about " + req.body.employee + " wearing a " + req.body.wearing,
    temperature: 0.9,
    max_tokens: 720,
    top_p: 1.0,
    frequency_penalty: 0.0,
    presence_penalty: 0.0
  });
  res.status(200).json({ result: completion.data.choices[0].text });
}

• 错误日志、控制台截图如下：

: [WritableState],
      _events: [Object: null prototype],
      _eventsCount: 3,
      _maxListeners: undefined,
      _options: [Object],
      _ended: true,
      _ending: true,
      _redirectCount: 0,
      _redirects: [],
      _requestBodyLength: 142,
      _requestBodyBuffers: [],
      _onNativeResponse: [Function (anonymous)],
      _currentRequest: [Circular *1],
      _currentUrl: 'https://api.openai.com/v1/engines/text-curie-001/completions',
      [Symbol(kCapture)]: false
    },
    [Symbol(kCapture)]: false,
    [Symbol(kNeedDrain)]: false,
    [Symbol(corked)]: 0,
    [Symbol(kOutHeaders)]: [Object: null prototype] {
      accept: [Array],
      'content-type': [Array],
      'user-agent': [Array],
      authorization: [Array],
      'content-length': [Array],
      host: [Array]
    }
  },
  response: {
    status: 401,
    statusText: 'Unauthorized',
    headers: {
      date: 'Tue, 21 Jun 2022 10:33:02 GMT',
      'content-type': 'application/json; charset=utf-8',
      'content-length': '280',
      connection: 'close',
      vary: 'Origin',
      'x-request-id': '5534283309335fe6e2bf1c0ed0c68c1d',
      'strict-transport-security': 'max-age=15724800; includeSubDomains'
    },
    config: {
      transitional: [Object],
      adapter: [Function: httpAdapter],
      transformRequest: [Array],
      transformResponse: [Array],
      timeout: 0,
      xsrfCookieName: 'XSRF-TOKEN',
      xsrfHeaderName: 'X-XSRF-TOKEN',
      maxContentLength: -1,
      maxBodyLength: -1,
      validateStatus: [Function: validateStatus],
      headers: [Object],
      method: 'post',
      data: '{"prompt":"Write a story about jack wearing a wallet","temperature":0.9,"max_tokens":720,"top_p":1,"frequency_penalty":0,"presence_penalty":0}',
      url: 'https://api.openai.com/v1/engines/text-curie-001/completions'
    },
    request: <ref *1> ClientRequest {
      _events: [Object: null prototype],
      _eventsCount: 7,
      _maxListeners: undefined,
      outputData: [],
      outputSize: 0,
      writable: true,
      destroyed: false,
      _last: true,
      chunkedEncoding: false,
      shouldKeepAlive: false,
      maxRequestsOnConnectionReached: false,
      _defaultKeepAlive: true,
      useChunkedEncodingByDefault: true,
      sendDate: false,
      _removedConnection: false,
      _removedContLen: false,
      _removedTE: false,
      _contentLength: null,
      _hasBody: true,
      _trailer: '',
      finished: true,
      _headerSent: true,
      _closed: false,
      socket: [TLSSocket],
      _header: 'POST /v1/engines/text-curie-001/completions HTTP/1.1\r\n' +
        'Accept: application/json, text/plain, */*\r\n' +
        'Content-Type: application/json\r\n' +
        'User-Agent: OpenAI/NodeJS/2.0.0\r\n' +
        'Authorization: Bearer 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\r\n' +
        'Content-Length: 142\r\n' +
        'Host: api.openai.com\r\n' +
        'Connection: close\r\n' +
        '\r\n',
      _keepAliveTimeout: 0,
      _onPendingData: [Function: nop],
      agent: [Agent],
      socketPath: undefined,
      method: 'POST',
      maxHeaderSize: undefined,
      insecureHTTPParser: undefined,
      path: '/v1/engines/text-curie-001/completions',
      _ended: true,
      res: [IncomingMessage],
      aborted: false,
      timeoutCb: null,
      upgradeOrConnect: false,
      parser: null,
      maxHeadersCount: null,
      reusedSocket: false,
      host: 'api.openai.com',
      protocol: 'https:',
      _redirectable: [Writable],
      [Symbol(kCapture)]: false,
      [Symbol(kNeedDrain)]: false,
      [Symbol(corked)]: 0,
      [Symbol(kOutHeaders)]: [Object: null prototype]
    },
    data: { error: [Object] }
  },
  isAxiosError: true,
  toJSON: [Function: toJSON]
}
END RequestId: 427a64bf-859c-4f86-b3ca-33e5017aa24d
REPORT RequestId: 427a64bf-859c-4f86-b3ca-33e5017aa24d  Duration: 697.32 ms Billed Duration: 698 ms Memory Size: 1024 MB    Max Memory Used: 45 MB  
RequestId: 427a64bf-859c-4f86-b3ca-33e5017aa24d Error: Runtime exited with error: exit status 1
Runtime.ExitError

根因定位 #

1. 最高优先级风险：API密钥已完全泄露
   日志中明文打印了完整的OpenAI API密钥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，该密钥已被公开，大概率已被OpenAI自动吊销，或被他人盗用，所有携带该密钥的请求都会返回401未授权错误。
2. 401错误直接诱因
   Vercel环境中配置的OPENAI_API_KEY值无效：要么是填入的密钥本身错误、已过期/被吊销，要么是配置环境变量后未重新部署，导致函数运行时读取不到正确的密钥值。
3. 500错误直接诱因
   代码未对OpenAI接口请求做异常捕获，当接口返回401错误时，未捕获的Promise异常直接导致Vercel Serverless函数进程崩溃退出，最终对外返回通用500错误，而非真实的401错误信息。

修复步骤 #

1. 立刻作废泄露的旧密钥 #

登录OpenAI控制台进入API密钥管理页面，找到上述已泄露的sk-tVy7开头的密钥，立即删除作废，避免被他人盗用消耗账号额度。

2. 生成新密钥并正确配置Vercel环境变量 #

• 在OpenAI控制台生成新的API密钥，生成后立即复制保存（新密钥仅展示一次，关闭页面后无法再次查看）
• 进入Vercel对应项目的Settings - Environment Variables页面，新增/更新OPENAI_API_KEY变量，值填入刚生成的新密钥，生效范围勾选Production、Preview、Development全环境
• 注意：环境变量配置完成后必须手动触发一次重新部署，新的环境变量才会注入到函数运行环境中

3. 优化接口代码，增加异常处理与入参校验 #

将原有接口代码替换为以下版本，避免未捕获异常导致函数崩溃，同时方便后续排查问题：

import { Configuration, OpenAIApi } from "openai";

const configuration = new Configuration({
  apiKey: process.env.OPENAI_API_KEY,
});
const openai = new OpenAIApi(configuration);

export default async function (req, res) {
  // 入参合法性校验
  if (!req.body.employee?.trim() || !req.body.wearing?.trim()) {
    return res.status(400).json({ error: "缺少必要的生成参数" });
  }
  if (!process.env.OPENAI_API_KEY) {
    return res.status(500).json({ error: "服务端API密钥未配置" });
  }

  try {
    const completion = await openai.createCompletion("text-curie-001", {
      prompt: "Write a story about " + req.body.employee + " wearing a " + req.body.wearing,
      temperature: 0.9,
      max_tokens: 720,
      top_p: 1.0,
      frequency_penalty: 0.0,
      presence_penalty: 0.0
    });
    res.status(200).json({ result: completion.data.choices[0].text.trim() });
  } catch (error) {
    // 打印详细错误日志用于排查，同时向前端返回结构化错误
    console.error("OpenAI接口调用失败：", error.response?.data || error.message);
    const statusCode = error.response?.status || 500;
    res.status(statusCode).json({
      error: error.response?.data?.error?.message || "服务内部错误，请稍后重试"
    });
  }
}

4. 重新部署验证 #

提交代码更新后触发Vercel自动部署，部署完成后重新测试功能即可。

内容的提问来源于stack exchange，提问作者Sambuxc