调用OpenAI Chat Completions API遇400错误请求，求排查原因

我尝试调用OpenAI的Chat Completions API（使用gpt-3.5-turbo模型），但收到了400 Bad Request错误。

我的调用代码（C#） #

var body = new
{
    model = "gpt-3.5-turbo",
    messages = data
};

string jsonMessage = JsonConvert.SerializeObject(body);

using (HttpClient client = new HttpClient())
{
    ServicePointManager.SecurityProtocol = SecurityProtocolType.Tls12;

    HttpRequestMessage requestMessage = new HttpRequestMessage(HttpMethod.Post, "https://api.openai.com/v1/completions")
    {
        Content = new StringContent(jsonMessage, Encoding.UTF8, "application/json")
    };

    string api_key = PageExtension_CurrentUser.Community.CAIChatGPTAPIKey.Length > 30 
        ? PageExtension_CurrentUser.Community.CAIChatGPTAPIKey 
        : Genesis.Generic.ReadAppSettingsValue("chatGPTAPIKey");
    requestMessage.Headers.Add("Authorization", $"Bearer {api_key}");

    HttpResponseMessage response = client.SendAsync(requestMessage).Result;
    if (response.StatusCode == HttpStatusCode.OK)
    {
        string responseData = response.Content.ReadAsStringAsync().Result;
        dynamic responseObj = JsonConvert.DeserializeObject(responseData);
        string choices = responseObj.choices[0].text;
    }
}

OpenAI官方示例代码 #

curl示例 #

curl https://api.openai.com/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -d '{
  "model": "gpt-3.5-turbo",
  "messages": [{"role": "user", "content": "Hello!"}]
}'

Python示例 #

openai.ChatCompletion.create(
  model="gpt-3.5-turbo",
  messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Who won the world series in 2020?"},
        {"role": "assistant", "content": "The Los Angeles Dodgers won the World Series in 2020."},
        {"role": "user", "content": "Where was it played?"}
    ]
)

收到的错误响应 #

{StatusCode: 400, ReasonPhrase: 'Bad Request', Version: 1.1, Content: System.Net.Http.StreamContent, Headers:
{
  Connection: keep-alive
  Access-Control-Allow-Origin: *
  Openai-Organization: user-lmjzqj7ba2bggaekkhr68aqn
  Openai-Processing-Ms: 141
  Openai-Version: 2020-10-01
  Strict-Transport-Security: max-age=15724800; includeSubDomains
  X-Request-Id: 9eddf8bb8dcc106ca11d44ad7f8bbecc
  Date: Mon, 06 Mar 2023 12:49:46 GMT
  Content-Length: 201
  Content-Type: application/json
}}

{Method: POST, RequestUri: 'https://api.openai.com/v1/chat/completions', Version: 1.1, Content: System.Net.Http.StringContent, Headers:
{
  Authorization: Bearer sk-ihUxxxxxxxxxxxxxxxxxx[JUST REMOVED MY API KEY]xxxxxxxxxxxxxxx
  Content-Type: application/json; charset=utf-8
  Content-Length: 79
}}

错误原因分析 #

1. API端点错误：你的代码中请求的是https://api.openai.com/v1/completions，这是文本补全类模型（如gpt-3.5-turbo-instruct）的接口端点。而gpt-3.5-turbo对应的Chat Completions API正确端点是https://api.openai.com/v1/chat/completions，这是触发400错误的核心原因。

2. 响应字段解析错误：即使修正端点，当前代码中responseObj.choices[0].text的写法也不符合Chat Completions API的返回结构。该接口的响应内容嵌套在message.content字段下，正确取值应为responseObj.choices[0].message.content（text是文本补全接口的返回字段）。

3. messages格式校验：需额外确认data变量的结构是否合规，每个消息对象必须包含role（可选值：system、user、assistant）和content字段，格式示例：[{"role":"user","content":"你的问题内容"}]，格式不符也会触发400错误。

内容的提问来源于stack exchange，提问作者Robert Benedetto