Any HTTP client can use ProxyLLM.
You do not need an SDK. Anything that can send an HTTPS request can call ProxyLLM's OpenAI-compatible API. OpenAI-model requests run through Codex Hosted on your ChatGPT subscription, with scoped keys and budget caps.
$129/month SaaS. Bring your own model keys. No inference markup.
Three steps to connect.
Create a service key
Generate a ProxyLLM key for the system calling the REST API. Use separate keys for web apps, workers, and internal tools.
Call the OpenAI-compatible route
Send requests to https://api.proxyllm.ai/v1/chat/completions with your ProxyLLM key as the bearer token.
Use any HTTP client
curl, fetch, Postman, low-code HTTP steps, and backend services hit the same endpoint and share the same logs, caps, and Codex Hosted billing.
POST chat completions.
Use your ProxyLLM key and the gateway base URL from any runtime.
curl https://api.proxyllm.ai/v1/chat/completions \
-H "Authorization: Bearer pk_live_..." \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o-mini",
"messages": [{ "role": "user", "content": "Extract the invoice total." }]
}'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.
One API surface for every caller.
Keep model access consistent across scripts, workers, tools, and services without sharing provider keys everywhere.