cURL

使用 cURL 命令行直接调用 WLON API，适合快速测试和脚本集成。

基本请求

发送一个 Chat Completions 请求到 /v1/chat/completions：

curl https://api2everything.xyz/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "system", "content": "你是一个有帮助的助手。"},
      {"role": "user", "content": "你好！"}
    ]
  }'

请求头说明

JSON 请求体

完整参数示例：

curl https://api2everything.xyz/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "system", "content": "你是一个翻译助手。"},
      {"role": "user", "content": "翻译成英文：今天天气真好"}
    ],
    "temperature": 0.7,
    "max_tokens": 2048,
    "top_p": 1.0
  }'

流式输出

在请求体中添加 "stream": true，并使用 -N 禁用缓冲，实时显示输出：

curl -N https://api2everything.xyz/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "写一首关于春天的诗"}
    ],
    "stream": true
  }'

使用 jq 解析响应

使用 jq 从 JSON 响应中提取内容：

# 提取回复文本
curl -s https://api2everything.xyz/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "1+1=?"}]
  }' | jq -r '.choices[0].message.content'

# 提取 token 用量信息
curl -s https://api2everything.xyz/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "你好"}]
  }' | jq '.usage'

查询可用模型

curl https://api2everything.xyz/v1/models \
  -H "Authorization: Bearer sk-your-api-key" | jq '.data[].id'

使用环境变量

将 API Key 存入环境变量，简化命令：

# 设置环境变量
export OPENAI_API_KEY="sk-your-api-key"

# 之后的请求中引用变量
curl https://api2everything.xyz/v1/chat/completions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "你好！"}]
  }'