Scenarios that run all day, on a flat AI bill.
Make runs unattended, which is exactly where per-token billing stings. Point a scenario at ProxyLLM and its OpenAI calls run through Codex Hosted on your ChatGPT subscription, behind a scoped key with a hard cap.
$129/month SaaS. Bring your own model keys. No inference markup.
Three steps to connect.
Create an automation key
Generate a ProxyLLM key for Make and set a monthly cap. Scenario loops and retries should have their own boundary.
Use an HTTP or OpenAI-compatible module
Send chat completions to https://api.proxyllm.ai/v1/chat/completions with your ProxyLLM key as the bearer token.
Track scenario cost
Each scenario request is attributed to the Make key, so you can see automation spend separately from product traffic.
Call the chat completions endpoint.
Use Make's HTTP module or any OpenAI-compatible module that lets you set the base URL.
POST https://api.proxyllm.ai/v1/chat/completions
Authorization: Bearer pk_live_...
Content-Type: application/json
{
"model": "gpt-4o-mini",
"messages": [{ "role": "user", "content": "Classify this lead." }]
}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.
Automate without open-ended spend.
Classification, enrichment, and extraction steps bill to your ChatGPT subscription through Codex Hosted. When a plan limit hits, your own OpenAI key picks up until it resets.