Chat completions (Python)

Send an ordered array of messages to chat.completions.create. The response contains choices; usage, when returned, reports token consumption.

This guide uses the official OpenAI client with TheRouter; it is not a TheRouter-owned SDK. The therouter and @therouter/sdk packages previously named here are not currently published in the public package registries.

pip install openai

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["THEROUTER_API_KEY"], base_url="https://api.therouter.ai/v1")
completion = client.chat.completions.create(
    model="openai/gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello!"}],
    max_tokens=32,
)
print(completion.choices[0].message.content)