Python SDK

Use the official OpenAI Python SDK with GonkaGate. No custom SDK required.

For API keys, base URL, and your first request, start with the Quickstart guide .

Installation

Install the official OpenAI Python SDK:

terminal

pip install openai

Configuration

Configure the client to use GonkaGate's API endpoint:

config.py

from openai import OpenAI

client = OpenAI(
    base_url="https://api.gonkagate.com/v1",
    api_key="gp-your-api-key"
)

Basic Usage

Make your first chat completion request:

basic_usage.py

from openai import OpenAI

client = OpenAI(
    base_url="https://api.gonkagate.com/v1",
    api_key="gp-your-api-key"
)

response = client.chat.completions.create(
    model="qwen/qwen3-235b-a22b-instruct-2507-fp8",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello, how are you?"}
    ],
    temperature=0.7,
    max_tokens=1000
)

print(response.choices[0].message.content)

Async Usage

Use async/await for non-blocking requests:

async_usage.py

import asyncio
from openai import AsyncOpenAI

async def main():
    client = AsyncOpenAI(
        base_url="https://api.gonkagate.com/v1",
        api_key="gp-your-api-key"
    )

    response = await client.chat.completions.create(
        model="qwen/qwen3-235b-a22b-instruct-2507-fp8",
        messages=[{"role": "user", "content": "Hello!"}]
    )

    print(response.choices[0].message.content)

asyncio.run(main())

Language-specific notes

A few Python-specific tips before you ship:

Use AsyncOpenAI for concurrent workloads.
Set request timeouts to avoid hanging tasks.
Keep API keys on the server (not in notebooks or front-end).

See Streaming and Error handling for real-time responses and retry guidance.