基础接口地址
https://newapi.xingk.xyz/v1/chat/completions
兼容OpenAI标准格式
完全适配OpenAI官方请求/返回结构，可直接替换openai客户端地址无缝调用
请求头配置
Content-Type: application/json
Authorization: Bearer 你的密钥key
key请向平台申请获取，无密钥无法调用接口
标准POST请求示例（JSON）
{
"model": "gpt-3.5-turbo",
"messages": [
{
"role": "system",
"content": "你是专业智能助手"
},
{
"role": "user",
"content": "你好，介绍下自己"
}
],
"temperature": 0.7,
"max_tokens": 1024,
"stream": false
}
| 参数名 |
类型 |
说明 |
| model |
string |
模型标识，支持gpt3.5/gpt4系列标识 |
| messages |
array |
对话消息数组，role支持system/user/assistant |
| temperature |
float |
随机性0~1，越高回答越发散 |
| max_tokens |
int |
单次最大输出token数量 |
| stream |
bool |
true开启流式逐块返回，false一次性返回完整内容 |
非流式返回结果示例
{
"id": "chatcmpl-xxxxxxx",
"object": "chat.completion",
"created": 1788888888,
"model": "gpt-3.5-turbo",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "您好，我是基于xingk接口的AI助手，能够为你解答各类问题..."
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 22,
"completion_tokens": 45,
"total_tokens": 67
}
}
流式Stream返回片段示例
data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1788888888,"model":"gpt-3.5-turbo","choices":[{"index":0,"delta":{"content":"您好"},"finish_reason":null}]}
data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1788888888,"model":"gpt-3.5-turbo","choices":[{"index":0,"delta":{"content":"，我是"},"finish_reason":null}]}
data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1788888888,"model":"gpt-3.5-turbo","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
data: [DONE]
Python调用示例（openai库）
# 安装依赖 pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://newapi.xingk.xyz/v1",
api_key="填入你的key"
)
resp = client.chat.completions.create(
model="gpt-3.5-turbo",
messages=[{"role":"user","content":"hello"}]
)
print(resp.choices[0].message.content)
访问注意事项
1. 所有请求必须HTTPS，HTTP请求会被拦截；
2. 完全兼容OpenAI SDK、各类第三方客户端、AI绘画对话工具；
3. 流量、额度、计费规则以平台公告为准；
4. 出现401代表密钥错误/过期，429代表调用频率超限。