通用对话接口（Chat Completions）
POST https://ai.amaxsmp.com/v1/chat/completions兼容 OpenAI Chat Completions API，用于大语言模型（LLM）的普通对话（非流式）。
请求示例
cURL
curl https://ai.amaxsmp.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
-d '{
"model": "gpt-4o",
"messages": [
{"role": "system", "content": "你是一个有帮助的AI助手。"},
{"role": "user", "content": "什么是API网关？"}
],
"temperature": 0.7,
"max_tokens": 500
}'Python（OpenAI SDK）
from openai import OpenAI
client = OpenAI(
base_url="https://ai.amaxsmp.com/v1",
api_key="sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
)
response = client.chat.completions.create(
model="gpt-4o",
messages=[
{"role": "system", "content": "你是一个有帮助的AI助手。"},
{"role": "user", "content": "什么是API网关？"}
],
temperature=0.7,
max_tokens=500
)
print(response.choices[0].message.content)JavaScript
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://ai.amaxsmp.com/v1",
apiKey: "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
});
const response = await client.chat.completions.create({
model: "gpt-4o",
messages: [
{ role: "system", content: "你是一个有帮助的AI助手。" },
{ role: "user", content: "什么是API网关？" },
],
temperature: 0.7,
max_tokens: 500,
});
console.log(response.choices[0].message.content);请求参数
| 参数 | 类型 | 必填 | 说明 |
|---|---|---|---|
model | string | 是 | 模型名，如 gpt-4o、claude-sonnet-4-6，或 amax-router |
messages | array | 是 | 对话消息列表 |
temperature | float | 否 | 采样温度，0~2，默认值因模型而异 |
max_tokens | int | 否 | 最大输出 Token 数 |
top_p | float | 否 | 核采样参数，0~1 |
n | int | 否 | 生成回复数量，默认 1 |
stop | string/array | 否 | 停止词 |
响应示例
{
"id": "chatcmpl-xxxxxxxx",
"object": "chat.completion",
"created": 1710000000,
"model": "gpt-4o",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "API网关是一个位于客户端和后端服务之间的中间层……"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 35,
"completion_tokens": 50,
"total_tokens": 85
}
}