Batch jobs and notebooks, without the token meter.
Point the official OpenAI Python client at ProxyLLM and keep your existing request shape. Scripts, notebooks, and workers send OpenAI calls through Codex Hosted, with budget caps and your own key as fallback.
$129/month SaaS. Bring your own model keys. No inference markup.
Three steps to connect.
Create a ProxyLLM key
Generate a scoped key for your script, notebook, worker, or batch job. Add a monthly cap when the caller can run unattended.
Swap the client base URL
Set base_url to https://api.proxyllm.ai/v1 and use your ProxyLLM key. The official OpenAI Python client does not need a wrapper.
Run calls on your subscription
With your ChatGPT account connected, OpenAI calls bill to the subscription through Codex Hosted. Your own API key covers anything past a plan limit.
One Python client.
Use your ProxyLLM key and base URL. Keep the OpenAI chat completions API.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.proxyllm.ai/v1",
api_key=os.environ["PROXYLLM_API_KEY"],
)
result = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "Extract the action items."}],
)
print(result.choices[0].message.content)Run your AI workloads on your ChatGPT subscription.
ProxyLLM runs OpenAI's Codex for you, signed in with your own ChatGPT account. Your apps call one OpenAI-compatible endpoint and the work bills to your flat plan instead of per-token API pricing.
Move batch work off metered billing.
Python jobs are where flat billing pays off: repeated prompts, long batch runs, and unattended loops, each under a spending cap.