MarkUDown
Deep Research API — MarkUDown AI research API docs
POST
/api/deep-researchDeep Research
Scrape the URLs you provide and have an LLM synthesize them into one research answer, with its sources.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| query | string | required | — | Research question or topic. |
| urls | array<string> | required | — | Source pages to scrape and analyze. Each URL costs 1 credit. |
| max_tokens | integer | optional | 4096 | Maximum length of the generated answer, in tokens. |
| timeout | integer | optional | 180 | Timeout in seconds. |
| callback_url | string | optional | null | Webhook URL to POST the result to when the job completes. |
Request
{
"query": "Which books in the catalogue cost less than £20?",
"urls": [
"https://books.toscrape.com/",
"https://books.toscrape.com/catalogue/page-2.html"
]
}Response
// POST returns { "success": true, "id": "abc123", "url": "/api/deep-research/abc123" }
// Poll GET /api/deep-research/{id} — "data" when completed:
{
"success": true,
"research": "## Books under £20\n\n...",
"sources": [
"https://books.toscrape.com/",
"https://books.toscrape.com/catalogue/page-2.html"
],
"pages_analyzed": 2
}