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.

The Stealth Agent (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 on preset. You pick the preset that matches your output, and the agent picks the right pipeline.
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:
FieldWhat it is
resultFinal humanized content as markdown. The exact same content stored against documentId.
runIdServer-side identifier of the run. Useful for support tickets and future replay endpoints.
documentIdIdentifier of the persisted document for this run.
presetEchoes your input preset.
outputWordsWord count of result, used for billing.
creditsSpentceil(outputWords × 10) Stealth API words charged for this run.
remainingCreditsPrepaid balance after the charge.
billingMode"prepaid" or "payg".
meteredChargedCreditsWords billed to metered usage (0 when fully prepaid).
See the endpoint reference for the complete schema and error codes.

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.
See Pricing for full rate cards and tiers.

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.