The Stealth Agent (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.
POST /api/stealthify/agent) is StealthGPT’s premium long-form content endpoint. It replaces the legacy business: true flag on /api/stealthify with a complete generation pipeline that researches the topic, drafts the content, optionally fact-checks it, humanizes the prose, and (optionally) inserts images — all in a single request.
If you used to enable business: true for higher-quality output, this is your migration target.
Endpoint reference
POST https://stealthgpt.ai/api/stealthify/agent — full request/response schema, status codes, and language-specific examples.Why Stealth Agent
A single-pass humanizer (the/api/stealthify endpoint) is excellent at rewriting text you already have. For long-form generation where the model has to plan, research, cite, and write from scratch, a single pass is not enough. The Stealth Agent runs each step as a dedicated stage with its own model, prompt, and validation:
Researched, not invented
Web research grounds the draft in real sources before the writing model sees the prompt, reducing hallucinations.
Optional fact-checking
enableFactCheck: true runs an additional pass that verifies claims and rewrites unsupported ones before humanization.Humanized last
Humanization runs after drafting and fact-checking, so the final text reads naturally and stays low-detection.
Format-aware output
Each preset returns markdown shaped for its medium — academic structure with citations, SEO sections with headings, or platform-tuned social posts.
Presets
The endpoint accepts a discriminated union onpreset. You pick the preset that matches your output, and the agent picks the right pipeline.
- academic
- seo
Use for: essays, literature reviews, study-guide style explainers, research-paper drafts.Pipeline: web research → academic draft → optional fact-check → humanize → academic post-processing (citations + optional images).Returns markdown with citations formatted in your chosen style (APA by default).
What you get back
Every successful run returns a single JSON payload (200 OK) containing the final markdown plus billing metadata:
| Field | What it is |
|---|---|
result | Final humanized content as markdown. The exact same content stored against documentId. |
runId | Server-side identifier of the run. Useful for support tickets and future replay endpoints. |
documentId | Identifier of the persisted document for this run. |
preset | Echoes your input preset. |
outputWords | Word count of result, used for billing. |
creditsSpent | ceil(outputWords × 10) Stealth API words charged for this run. |
remainingCredits | Prepaid balance after the charge. |
billingMode | "prepaid" or "payg". |
meteredChargedCredits | Words billed to metered usage (0 when fully prepaid). |
Billing model
Stealth Agent uses the same Stealth API balance and pay-as-you-go rules as/api/stealthify, but charges by output:
creditsSpent = ceil(outputWords × 10)— input length does not change the price.- Billing falls back from prepaid balance to pay-as-you-go automatically when terms are accepted and a payment method is on file.
- Cancelled requests (HTTP
499) are not charged.
How long does a run take
Stealth Agent runs are multi-step and can take several minutes. The server allows up to 600 seconds per request. Configure your HTTP client with a timeout of at least 10 minutes — most clients default to 30–60s and will abort prematurely. The usage guide walks through timeout configuration, balance preflight checks, error recovery, and idempotency considerations end-to-end.Next steps
Usage guide
End-to-end walkthrough: pick a preset, configure the client, handle errors, and ship to production.
Use cases
Concrete prompts and recommended preset/option combinations for common workflows.
Endpoint reference
Request bodies per preset, response fields, error codes, and curl/Python/Node.js examples.