n8n Platform integration · n8n

Use your ChatGPT subscription inside every n8n workflow.

n8n's OpenAI credential has a Base URL field. Point it at ProxyLLM once and every AI node in every workflow runs through Codex Hosted, billed to your ChatGPT subscription. No community nodes, no HTTP Request workarounds.

$129/month SaaS. Bring your own model keys. No inference markup.

Three steps to connect.

01

Create a ProxyLLM key

Generate a key in the dashboard. Give n8n its own scoped key with a monthly budget cap so a runaway workflow cannot surprise you.

02

Edit the OpenAI credential

In n8n go to Credentials → OpenAI. Paste the ProxyLLM key as the API Key and set the Base URL to https://api.proxyllm.ai/v1. That is the whole integration.

03

Run your workflows

Every OpenAI and OpenAI Chat Model node now flows through ProxyLLM. Bare OpenAI model names run on Codex Hosted; prefixed names like anthropic/ and google/ reach Claude and Gemini through your connected keys.

Two fields in one credential.

Use n8n's built-in OpenAI credential. Nothing else changes.

n8n · Credentials · OpenAI Connection tested
API Key pk_live_••••••••••••••••
Base URL https://api.proxyllm.ai/v1
Codex Hosted · the main feature

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.

$129/month · normal SaaS pricing

Your automations, off the per-token meter.

Classify, extract, and summarize steps run all day in n8n. Through Codex Hosted they bill to the flat ChatGPT plan you already pay for, and your own API key takes over at plan limits.