Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.stealthgpt.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Optimizing Tone Selection

StealthGPT offers several tone options to match your content needs:

Tone Options

Standard

Default tone for general-purpose content. Balanced readability and formality.

HighSchool

Simpler style with occasional grammatical errors. High on Flesch-Kincaid Readability.

College

Semi-complex style with occasional minor errors. Medium Flesch-Kincaid score.

PhD

Complex, sophisticated style. No grammatical errors. Low Flesch-Kincaid score.
Choose the tone that best matches your target audience and content requirements.

​
Detector Parameter (Deprecated)

The detector parameter is deprecated and kept only for backward compatibility.

Detector Parameter

Unified Stealth Engine

All requests now use a single stealth model optimized for general AI detection avoidance. The detector value (e.g. "turnitin" or "gptzero") no longer changes model behavior and can be safely omitted.

​
Humanizer Model Selection

Use the model parameter to choose between the full stealth pipeline and a faster cleanup pass:

Model Options

heavy

Default. Runs the full StealthGPT humanizer pipeline and is designed for AI detector bypass.

lite

Fast AI-smell cleanup that keeps the text mostly unchanged. This mode is not designed to bypass AI detectors.
{
  "prompt": "Your text here",
  "rephrase": true,
  "model": "heavy"
}

​
Crafting Effective Prompts

The quality of generated content depends significantly on your prompt. Here are some techniques to improve your prompts:
Instead of: “Write about cars”Try: “Write about the environmental impact of electric vehicles compared to traditional combustion engines”
Instead of: “Write a product description”Try: “Write a product description for a premium leather wallet targeted at young professionals who value both style and functionality”
Instead of: “Write about climate change”Try: “Create a 5-point listicle about practical steps individuals can take to reduce their carbon footprint”
Instead of: “Write about cryptocurrency”Try: “Explain cryptocurrency concepts in a conversational tone as if speaking to someone with no technical background”

​
Output Format

Control the formatting of the returned content with the outputFormat parameter:

Output Format Options

text

Default format. Returns plain text without markdown formatting.

markdown

Returns formatted content with markdown syntax (headings, lists, bold, etc.).
{
  "prompt": "Write a summary of quantum computing",
  "rephrase": false,
  "outputFormat": "markdown"
}

​
Content Length Optimization

For optimal performance, we recommend keeping responses under 2,000 characters. When you need longer content:
  1. Break down your content needs into smaller, focused requests
  2. Use the /api/stealthify/articles endpoint for complete blog articles
  3. Chain multiple requests together, using the output of one as input for another

​
Using Templates

You can include templates in your prompts to guide the structure of generated content: 
{
  "prompt": "Please write an email following this template:\n\nSubject: [Product] - New Features\n\nHello [Name],\n\nI'm excited to share the latest updates to [Product]...\n\nBest regards,\n[Your Name]",
  "rephrase": false
}

​
Iterative Rephrasing

For maximum undetectability, consider an iterative approach:
1

Generate Initial Content

Create the first version of your content with rephrase: false
2

First Rephrasing

Submit the generated content with rephrase: true
3

Second Rephrasing

For even higher undetectability, submit the rephrased content for another round
Too many rephrasing iterations may affect content coherence or meaning. Test and find the optimal balance.

​
Multilingual Support

StealthGPT automatically detects the language of your input and routes it through a unified language engine:
  • For English input, content is processed directly with no additional translation.
  • For non-English input, the text is first translated to English, humanized, then:
    • If isMultilingual is true (default), translated back into the original language.
    • If isMultilingual is false, returned in humanized English.
To use this effectively, keep isMultilingual at its default (true) unless you specifically want English-only output for non-English prompts.

​
Premium Quality with Stealth Agent

Business mode has been removed from /api/stealthify and replaced by the Stealth Agent endpoint. The business field is still accepted in request bodies for backward compatibility, but it has no effect: all /api/stealthify requests run on the standard engine and are billed at the standard rate.
When undetectability and quality are paramount, send the prompt to POST /api/stealthify/agent instead. The Stealth Agent runs a multi-step pipeline (research → draft → optional fact-check → humanize → optional images) that consistently produces higher-quality, more grounded, and harder-to-detect long-form content than a single-pass humanizer can.

Academic preset

Essays, literature reviews, and research-style writing with auto-formatted citations.

SEO preset

Long-form blog posts grounded in keyword research and competitor analysis.

Social preset

LinkedIn or Medium posts that match each platform’s voice and structure.
See the Stealth Agent overview, usage guide, and use cases for details. Billing is ceil(outputWords × 10) Stealth API words per successful run; see Pricing.