API 使用

WalkAI 兼容 OpenAI API 格式，支持 Chat Completions 和 Responses API。

接入地址

配置项	值
Base URL	https://walkai.top

TIP

部分第三方平台或 SDK 要求 Base URL 以 /v1 结尾，填写 https://walkai.top/v1 即可。

Chat Completions

curl https://walkai.top/v1/chat/completions \
  -H "Authorization: Bearer sk-你的密钥" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [{"role": "user", "content": "你好"}],
    "stream": true
  }'

Responses API

curl https://walkai.top/v1/responses \
  -H "Authorization: Bearer sk-你的密钥" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "input": "写一个快速排序"
  }'

模型列表

curl https://walkai.top/v1/models \
  -H "Authorization: Bearer sk-你的密钥"

使用 OpenAI SDK

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-你的密钥",
    base_url="https://walkai.top/v1"
)

response = client.chat.completions.create(
    model="gpt-5.4",
    messages=[{"role": "user", "content": "你好"}]
)
print(response.choices[0].message.content)

Node.js

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-你的密钥',
  baseURL: 'https://walkai.top/v1',
});

const response = await client.chat.completions.create({
  model: 'gpt-5.4',
  messages: [{ role: 'user', content: '你好' }],
});
console.log(response.choices[0].message.content);

推理等级

部分模型支持 reasoning_effort 参数：

{
  "model": "gpt-5.5",
  "reasoning_effort": "high",
  "messages": [{"role": "user", "content": "复杂推理问题"}]
}

可选值：low / medium / high / xhigh。等级越高首字越慢，详见 支持的模型。