Quickstart

Use a key from the console with the standard OpenAI-compatible API. The examples use placeholders; do not paste a real key into source code or a browser application.

Prepare

1. Create a dedicated API key in the console.
2. Use https://1pkapi.com/v1 as the base URL.
3. Get an applicable model ID from GET /v1/models for the current key.

Send a short curl request

curl https://1pkapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "your-model-id",
    "messages": [{"role": "user", "content": "Reply with one word: ready"}]
  }'

Use the Python OpenAI SDK

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ["ONEPK_API_KEY"],
    base_url="https://1pkapi.com/v1",
)

response = client.chat.completions.create(
    model="your-model-id",
    messages=[{"role": "user", "content": "Reply with one word: ready"}],
)
print(response.choices[0].message.content)

Verify before expanding

First confirm one short, non-streaming request. Then configure streaming or higher concurrency in the application. For a 401, 429, or availability error, collect the time, model, status code, and a redacted error message before retrying.