快速开始

测试时请使用以下值：

• 基地址：https://metaiolab.com/v1
• 模型：gpt-5.4
• API 密钥：你的 MetaioLab API 密钥

1. 测试模型列表

curl https://metaiolab.com/v1/models \
  -H "Authorization: Bearer sk-your-token"

预期结果：返回一个正常的模型列表。

2. 测试 OpenAI 兼容聊天接口

curl https://metaiolab.com/v1/chat/completions \
  -H "Authorization: Bearer sk-your-token" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [
      {"role": "user", "content": "Reply with only the text: chat ok"}
    ],
    "max_tokens": 32
  }'

预期结果：正常返回聊天补全，内容接近 chat ok。

3. 测试 OpenAI 兼容 Responses 接口

curl https://metaiolab.com/v1/responses \
  -H "Authorization: Bearer sk-your-token" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "input": "Reply with only the text: responses ok",
    "max_output_tokens": 32
  }'

预期结果：返回 Responses 风格的输出，文本接近 responses ok。

4. 测试 Anthropic 兼容 Messages 接口

curl https://metaiolab.com/v1/messages \
  -H "x-api-key: sk-your-token" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "max_tokens": 32,
    "messages": [
      {"role": "user", "content": "Reply with only the text: messages ok"}
    ]
  }'

预期结果：返回 Anthropic 风格的 messages 响应，文本接近 messages ok。