SkillRouter
Documentation menu

Start

Python

Use the standard OpenAI Python client with a SkillRouter base URL.

Install and configure

Shell
python -m pip install openai
export SKILLROUTER_API_KEY=sr_test_your_key
Python
import os

from openai import OpenAI

client = OpenAI(
    api_key=os.environ["SKILLROUTER_API_KEY"],
    base_url="https://api.useskillrouter.com/v1"
)

response = client.chat.completions.create(
    model="anthropic/claude-sonnet",
    messages=[
        {"role": "user", "content": "Audit this page for SEO."}
    ],
    extra_body={"skill": "seo-audit"}
)

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

Keep configuration on the server

  • Read the key from an environment variable or secret manager.
  • Set request timeouts for the workload and handle normalized SkillRouter errors.
  • Record the sr_req_* request ID when you need support or reconciliation.
  • Use the test key prefix for development and a separately limited live key for production.