Run Cursor on your ChatGPT subscription.
Cursor's OpenAI-compatible provider takes one base URL. Set it to ProxyLLM and your OpenAI-model calls run through Codex Hosted, billed to your flat ChatGPT subscription instead of per-token API pricing.
$129/month SaaS. Bring your own model keys. No inference markup.
Three steps to connect.
Create a Cursor key
Generate a scoped key in ProxyLLM for editor traffic. Give Cursor its own cap so autocomplete experiments and agent retries stay bounded.
Use an OpenAI-compatible provider
Configure Cursor's OpenAI-compatible endpoint with https://api.proxyllm.ai/v1 and your ProxyLLM key.
Code on your ChatGPT plan
Editor calls to OpenAI models run through Codex Hosted on your subscription. At a plan limit, ProxyLLM falls back to a second Codex account or your API key until it resets.
One endpoint in Cursor.
Use the ProxyLLM base URL anywhere Cursor asks for an OpenAI-compatible provider.
OPENAI_BASE_URL=https://api.proxyllm.ai/v1
OPENAI_API_KEY=pk_live_...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.
Already pay for ChatGPT? Code on it.
Connect your account with OpenAI's device-code login. Cursor gets a scoped key, a budget cap, and a request log for everything the editor sends.