Your ChatGPT subscription, serving production workloads.
ProxyLLM runs the official Codex CLI in a container only you use. Connect your account once and every OpenAI-compatible app you have can send work to it, billed to your flat plan instead of per token.
$129/month SaaS. Bring your own model keys. No inference markup.
Three steps to connect.
Connect your ChatGPT account
Sign in with OpenAI's device-code flow from the ProxyLLM dashboard. Your private Codex container starts in about a minute. We never see your password.
Add a fallback
Connect a second ChatGPT account or drop in your OpenAI API key. When your plan's limit hits, requests fail over automatically until it resets.
Call the endpoint
Point any OpenAI-compatible SDK at https://api.proxyllm.ai/v1 with your ProxyLLM key. Each request runs as a Codex job billed to your subscription.
Use the OpenAI-compatible endpoint.
Set the base URL and key. Requests run as Codex jobs inside your container.
export OPENAI_BASE_URL="https://api.proxyllm.ai/v1"
export OPENAI_API_KEY="$PROXYLLM_API_KEY"
# requests now run through your hosted Codex,
# billed to your ChatGPT subscriptionRun 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.
Stop metering what your plan already covers.
Connect your ChatGPT account, keep your API key as fallback, and watch the dashboard show what each request would have cost at API rates.