Skip to main content
StealthGPT ships an official, n8n-verified node, n8n-nodes-stealthgpt — listed on the n8n integrations directory. You can start full content-pipeline runs and humanize text directly from your n8n workflows. It uses the async API under the hood (start a run, then wait for completion or poll), which fits n8n’s long-running execution model.
This is a verified node, so it’s available on both self-hosted n8n and n8n Cloud. An instance owner enables it once (see Install); after that everyone on the instance can use it in their workflows.

Install

1

Open community nodes (instance owner)

In n8n, go to Settings → Community nodes → Install.
2

Install the verified node

Enter the package name and install:
As a verified node it installs cleanly on self-hosted and n8n Cloud.
3

Find the node

Add a new node and search for StealthGPT — it appears in the nodes panel for everyone on the instance.
Only an instance owner needs to do this one-time install. See n8n’s guide on using verified community nodes.

Credentials

Create a StealthGPT API credential:
  1. Add the StealthGPT node to a workflow and create a new credential when prompted.
  2. Paste your API token from the Stealth API dashboard.
  3. Save — n8n validates the token against your account balance.
Your API token lives only in your n8n credential store. It is never embedded in the node package.

Operations

The published n8n-nodes-stealthgpt 0.1.2 exposes two resources. The fields below were checked against that version on November 7, 2026.

Wait for completion

Both Start Run operations include a Wait for completion toggle:
  • On (default): the node starts the run and polls until it reaches a terminal state. A completed run outputs its result; failed or cancelled raises a node error. Tune the poll interval and max wait time in the node options for long pipeline runs.
  • Off: the node returns the runId and statusUrl immediately, so you can continue the workflow and check the run later with Get Run Status (useful with n8n’s Wait node or a scheduled poll).
Route completed text to factual, link and formatting review before publication. When polling manually, check the run’s status before passing its result to another node. The review recipes show the collection and approval handoff.

Use Super or bulk jobs through HTTP Request

Use n8n’s HTTP Request node to call the REST API when you want an explicit Super selection or bulk submission. Version 0.1.2 of the StealthGPT node exposes Heavy and Lite for humanization and has no bulk operation. For a Super humanization run:
  1. Name the HTTP Request node Create StealthGPT Run, set its method to POST and its URL to https://www.stealthgpt.ai/api/stealthify/runs.
  2. Store your token in an n8n Header Auth credential with header name api-token. Send the body as JSON.
  3. Map your source draft into text and set the remaining fields as shown:
Save the returned runId and statusUrl. The statusUrl is a relative path. Configure a GET HTTP Request node with the URL expression {{ 'https://www.stealthgpt.ai' + $('Create StealthGPT Run').item.json.statusUrl }} and the same API credential. Referencing the create node keeps the URL available across repeated polls; use a Wait node between checks. Send completed results to your review destination and route failed or cancelled to your error handling. For create retries, send an unchanged request with the same idempotency-key; resume an accepted job with its saved run ID. For bulk work, call POST /api/stealthify/runs/bulk with 1–100 items and a stable idempotencyKey per item. Collect the current batch’s terminal results before submitting the next batch. The TypeScript/Python recipes provide the request shapes, retry behavior and result-review checks to adapt to your workflow.

Example workflows

  • RSS → SEO article → CMS draft: RSS Trigger → StealthGPT (Content Generation, seo) → your CMS/WordPress node to create a draft.
  • Webhook → Humanize → Docs/Slack: Webhook → StealthGPT (Text Humanization) → Google Docs / Slack.
  • Airtable brief → generate → store: Airtable Trigger → StealthGPT (Content Generation) → write the result back to Airtable.

Notes & limits

  • Runs use the API billing of the account that owns the token. Humanization counts input plus output words: Standard and Lite use a 1× multiplier, and Super uses 2.5×. Stealth Agent uses its own workflow meter; see API pricing.
  • Use Wait for completion, or save the run ID and poll later, to collect background work. Configure a wait deadline and keep the existing run reference when that deadline is reached.
  • For the underlying REST contract, see the async humanization runs and Stealth Agent async runs pages.