Integrations / OpenAI Python SDK

ConnectDocumented

Use Badgr with the OpenAI Python SDK

Change base_url and the key in the official OpenAI Python client. The rest of your code stays the same.

The steps follow the tool's documented settings. No tested run is recorded for this page yet.

Why use Badgr for OpenAI Python SDK

Badgr interface
AI API
Where OpenAI Python SDK fits
External SDK
Why Badgr
Compatible Python inference
  • Change base_url and the key. The rest of your OpenAI code, including streaming and error handling, stays.
  • Billed per request at the rate listed for the model.
  • The same account runs GPU jobs when a script needs more than an API call.

What you can do

  • Move an existing Python app to Badgr with a two-line change
  • Stream responses to a terminal or web client
  • Handle rate limits and errors with the SDK's built-in exceptions

Quickstart: Python streaming request

import os
from openai import OpenAI, APIStatusError

client = OpenAI(base_url="https://aibadgr.com/v1", api_key=os.environ["BADGR_API_KEY"])

try:
    stream = client.chat.completions.create(
        model="badgr-auto",
        messages=[{"role": "user", "content": "Say hello."}],
        stream=True,
    )
    for chunk in stream:
        print(chunk.choices[0].delta.content or "", end="")
except APIStatusError as err:
    print(f"Request failed: {err.status_code}")

How it works

  1. 1.Your code builds an OpenAI client with the Badgr base URL
  2. 2.The SDK sends the request to Badgr
  3. 3.Chunks stream back and print as they arrive

What you get

  • Chat completions and streamed text

Requirements

  • A Badgr API key, saved as BADGR_API_KEY (get one at /get-api-key)
  • Python 3.8 or newer
  • The openai package

What it costs

  • AI requests are billed per request at the rate listed for the model you choose (see Models). This page does not quote a fixed price.
  • Your application keeps control of how many requests it sends. Use the limits in your own tool to cap usage.

See pricing for how billing works.

Proof

No tested run is recorded for this integration yet. A receipt and example output will be added here after a real run, not before.

Troubleshooting

  • Still calling OpenAI

    An OPENAI_BASE_URL environment variable or a second client may be overriding your code. Print client.base_url.

  • AuthenticationError

    The key must be your Badgr key, not an OpenAI key.

  • 429 rate limit

    The SDK retries a few times by default. For heavier use, lower your request rate or add your own backoff.

Developer reference

Ready to start with OpenAI Python SDK?

Every run or service has a spending limit you set before it starts.