调用OpenAI GPT-3.5 Turbo API报错，请求无法通过寻求帮助

问题场景 #

调用OpenAI的Chat Completions API时返回错误，使用的curl命令如下：

curl https://api.openai.com/v1/chat/completions \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer $OPENAI_API_KEY" \
 -d '{
        "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?"}
        ]
     }'

返回错误信息 #

{
    "error": {
        "message": "This is not a chat model and thus not supported in the v1/chat/completions endpoint. Did you mean to use v1/completions?",
        "type": "invalid_request_error",
        "param": "model",
        "code": null
    }
}

排查与解决步骤 #

• 确认模型名称准确性：确保model参数值为gpt-3.5-turbo，不要混淆成gpt-3.5-turbo-instruct（该模型属于文本补全类，需使用v1/completions端点）。
• 验证API密钥权限：检查你的API密钥是否具备访问gpt-3.5-turbo模型的权限，部分受限账号或旧账号可能无法使用该聊天模型。
• 检查环境变量加载：确认$OPENAI_API_KEY环境变量已正确设置并被curl读取，可尝试直接将密钥字符串替换命令中的$OPENAI_API_KEY进行测试，排除环境变量加载失败的问题。
• 核对API端点：确认使用的端点是https://api.openai.com/v1/chat/completions，该端点确实支持gpt-3.5-turbo模型，若使用区域专属服务（如Azure OpenAI）需对应调整域名与参数。

内容的提问来源于stack exchange，提问作者Rocky-y