Quick Start

Use these values when testing:

• Base URL: https://metaiolab.com/v1
• Model: gpt-5.4
• API key: your MetaioLab API key

1. Test model listing

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

2. Test OpenAI-compatible chat

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
  }'

Expected result: a normal chat completion response with content similar to chat ok.

3. Test OpenAI-compatible responses

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
  }'

Expected result: a responses-style payload with output text similar to responses ok.

4. Test Anthropic-compatible messages

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"}
    ]
  }'

Expected result: an Anthropic-style messages response with content similar to messages ok.