聊天

对话补全接口，最常用的 AI 对话接口，兼容 OpenAI Chat Completions API。

创建聊天完成 POST

POST https://api.nassaapi.xyz/chat/completions

Authorization

Authorization: Bearer sk-xxxx
Content-Type: application/json

请求参数

参数	类型	必填	说明
model	string	✅	模型 ID，例：gpt-5.5 / gpt-5.3-codex
messages	array	✅	对话消息列表
temperature	number	❌	采样温度，0–2，默认 1
max_tokens	int	❌	最大生成 Token 数
top_p	number	❌	核采样
stream	bool	❌	是否流式返回，默认 false
stop	string | array	❌	停止序列
tools	array	❌	函数调用工具定义

messages 结构

支持的 role 类型：

• system — 系统提示，设定 AI 角色和行为
• user — 用户输入
• assistant — 模型回复（多轮对话上下文）
• tool — 工具调用返回结果

多模态内容（部分模型支持）：

[
  { "type": "text", "text": "请描述这张图片" },
  { "type": "image_url", "image_url": { "url": "https://example.com/image.jpg" } }
]

示例请求

cURL

curl -X POST "https://api.nassaapi.xyz/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxx" \
  -d '{
    "model": "gpt-5.5",
    "messages": [
      { "role": "system", "content": "你是一个有帮助的 AI 助手。" },
      { "role": "user",   "content": "你好，请介绍一下自己。" }
    ],
    "temperature": 0.7,
    "max_tokens": 1024,
    "stream": false
  }'

JavaScript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-xxxx',
  baseURL: 'https://api.nassaapi.xyz',
});

const response = await client.chat.completions.create({
  model: 'gpt-5.5',
  messages: [
    { role: 'system', content: '你是一个有帮助的 AI 助手。' },
    { role: 'user',   content: '你好，请介绍一下自己。' },
  ],
  temperature: 0.7,
  max_tokens: 1024,
});

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

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxxx",
    base_url="https://api.nassaapi.xyz"
)

response = client.chat.completions.create(
    model="gpt-5.5",
    messages=[
        {"role": "system", "content": "你是一个有帮助的 AI 助手。"},
        {"role": "user",   "content": "你好，请介绍一下自己。"}
    ],
    temperature=0.7,
    max_tokens=1024
)

print(response.choices[0].message.content)

Go

package main

import (
    "context"
    "fmt"
    "github.com/sashabaranov/go-openai"
)

func main() {
    config := openai.DefaultConfig("sk-xxxx")
    config.BaseURL = "https://api.nassaapi.xyz"
    client := openai.NewClientWithConfig(config)

    resp, _ := client.CreateChatCompletion(
        context.Background(),
        openai.ChatCompletionRequest{
            Model: "gpt-5.5",
            Messages: []openai.ChatCompletionMessage{
                {Role: "system", Content: "你是一个有帮助的 AI 助手。"},
                {Role: "user",   Content: "你好，请介绍一下自己。"},
            },
            Temperature: 0.7,
            MaxTokens:   1024,
        },
    )
    fmt.Println(resp.Choices[0].Message.Content)
}

响应（非流式）

200 成功：

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1677858242,
  "model": "gpt-5.5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "你好！我是一个 AI 助手，很高兴为你服务。"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 28,
    "completion_tokens": 18,
    "total_tokens": 46
  }
}

401 未授权：

{
  "error": {
    "message": "Invalid API key",
    "type": "authentication_error",
    "code": "invalid_api_key"
  }
}

流式响应（stream=true）

采用 Server-Sent Events (SSE) 格式：

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"role":"assistant","content":"你"},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"好"},"finish_reason":null}]}

data: [DONE]