# HushSearch > One API for every kind of web data: live search, page scraping and extraction, whole-site crawls, browser sessions, PDF/OCR conversion and cited research. 35 endpoints behind one API key, priced per call in credits. ## Essentials - Base URL: https://api.hushsearch.io - Authentication: send the header `X-API-Key: ` on every request. Keys are created in the dashboard (http://localhost:3000/dashboard/keys); new accounts get 500 free credits. - Paths: call them exactly as listed, including the trailing slash. The bare path returns a 307 redirect that POST clients and CORS preflights do not follow. - Every JSON response includes `credits_used`, `credits_remaining` and `response_time_ms`. - Errors: 401 missing/invalid key, 402 out of credits, 422 invalid body (FastAPI `detail`), 429 rate limited (honour `Retry-After`). Calls that fail on the server side are refunded. - Long work (crawls, research, batches): submit to `POST /v1/jobs/` and poll `GET /v1/jobs/{id}` or register a webhook. - MCP: core capabilities (search, scrape, extract, crawl, map, research, batch scrape, summarize, structured extract, OCR, Docling, browser, balance) are Model Context Protocol tools at `https://api.hushsearch.io/v1/mcp/`. MCP tool prices are listed in each tool's description and can differ from the REST prices below. - Agent skill: http://localhost:3000/skill.md. Every docs page is also available as Markdown at http://localhost:3000/md/docs/. ## Search Live web results, fused and reranked. - [Web Search](http://localhost:3000/docs/endpoints/search): `POST /v1/search/` — Live web results as clean JSON — titles, URLs, snippets, instant answers. (1 credit) - [Streaming Search](http://localhost:3000/docs/endpoints/streaming-search): `POST /v1/search/stream` — The same search, streamed as server-sent events while engines answer. (1 credit) - [Batch Search](http://localhost:3000/docs/endpoints/search-batch): `POST /v1/search/batch` — Up to many queries in one request; one credit per non-empty query. (1 credit / query) - [Find Similar](http://localhost:3000/docs/endpoints/similar): `POST /v1/search/similar` — Pages semantically similar to a URL or a passage of text. (1 credit) ## Answers & research Cited answers, multi-step research and context packs. - [Cited Answer](http://localhost:3000/docs/endpoints/answer): `POST /v1/answer/` — A grounded answer with numbered citations and a groundedness score. (4 credits) - [Deep Research](http://localhost:3000/docs/endpoints/research): `POST /v1/research/` — Plans sub-queries, reads sources and writes a cited report. (8 credits) - [Search & Summarize](http://localhost:3000/docs/endpoints/search-summarize): `POST /v1/search-and-summarize/` — Search plus a short synthesized summary with sources. (5 credits) - [Context Pack](http://localhost:3000/docs/endpoints/context): `POST /v1/context/` — A token-budgeted context pack for coding and RAG agents. (2 credits) - [Agent](http://localhost:3000/docs/endpoints/agent): `POST /v1/agent/` — Give a goal; get a cited result plus the searches used to reach it. (4 credits) ## Scrape & extract Any URL into clean Markdown or typed JSON. - [Scrape](http://localhost:3000/docs/endpoints/scrape): `POST /v1/scrape/` — One page as Markdown, HTML or text, with optional query highlights. (2 credits) - [Extract](http://localhost:3000/docs/endpoints/extract): `POST /v1/extract/` — Main content of a URL as clean Markdown plus metadata and links. (3 credits) - [Reader](http://localhost:3000/docs/endpoints/reader): `GET /v1/reader/` — Prefix-style URL → LLM-ready Markdown in a single GET. (2 credits) - [Contents](http://localhost:3000/docs/endpoints/contents): `POST /v1/contents/` — Text, highlights and summaries for a list of URLs. (2 credits / URL) - [Structured Extract](http://localhost:3000/docs/endpoints/structured-extract): `POST /v1/structured-extract/` — Typed JSON from a page using a schema or a plain-English prompt. (4 credits) - [Search + Extract](http://localhost:3000/docs/endpoints/search-extract): `POST /v1/search-extract/` — Search, rerank and extract structured fields from the top hits. (6 credits) - [Multi-URL Extract](http://localhost:3000/docs/endpoints/multi-extract): `POST /v1/multi-extract/` — One schema applied across many URLs, optionally grounded by search. (4 credits) ## Crawl & map Whole sites, link graphs and batches. - [Map](http://localhost:3000/docs/endpoints/map): `POST /v1/map/` — Every link discovered on a site, with sitemap enrichment. (1 credit) - [Crawl](http://localhost:3000/docs/endpoints/crawl): `POST /v1/crawl/` — Follow a site's links to a depth and return every page as Markdown. (3 credits) - [Crawl Pipeline](http://localhost:3000/docs/endpoints/crawl): `POST /v1/crawl/pipeline` — Map → filter → scrape in one call with include/exclude rules. (4 credits) - [Batch Scrape](http://localhost:3000/docs/endpoints/batch-scrape): `POST /v1/batch-scrape/` — Scrape many URLs in parallel; two credits per URL. (2 credits / URL) ## Browsers Live sessions, actions, screenshots and goal-driven agents. - [Screenshot](http://localhost:3000/docs/endpoints/screenshot): `POST /v1/screenshot/` — A rendered PNG of any page, viewport or full length. (3 credits) - [Browser Sessions](http://localhost:3000/docs/endpoints/browser): `POST /v1/browser/sessions` — Durable headless sessions: navigate, read content, cookies, evaluate. (3 credits) - [Browser Execute](http://localhost:3000/docs/endpoints/browser-execute): `POST /v1/browser-execute/` — Run a list of actions — click, type, scroll, wait, extract — in a session. (2 credits) - [Agent Scrape](http://localhost:3000/docs/endpoints/agent-scrape): `POST /v1/agent-scrape/` — A goal-driven browser that navigates until it can return clean content. (5 credits) ## Documents JS render → PDF → Docling: layout-aware Markdown, OCR and structure. - [Render → Docling](http://localhost:3000/docs/endpoints/render-extract): `POST /v1/render-extract/` — Renders JavaScript, captures a PDF and runs Docling for layout-aware Markdown. (6 credits) - [Docling Markdown](http://localhost:3000/docs/endpoints/docling-markdown): `POST /v1/docling-markdown/` — PDF, Office files or rendered pages into structured Markdown. (4 credits) - [Docling OCR](http://localhost:3000/docs/endpoints/docling-ocr): `POST /v1/docling-ocr/` — OCR for scanned documents and images, returned as Markdown. (3 credits) - [Docling Structured](http://localhost:3000/docs/endpoints/docling-structured): `POST /v1/docling-structured/` — The full Docling layout tree — headings, tables, reading order — as JSON. (6 credits) ## Platform Embeddings, rerank, jobs, monitors, entities and MCP. - [Embeddings](http://localhost:3000/docs/endpoints/embeddings): `POST /v1/embeddings/` — Dense vectors for one or many inputs; one credit per input. (1 credit / input) - [Rerank](http://localhost:3000/docs/endpoints/rerank): `POST /v1/rerank/` — Score documents against a query with a cross-encoder. (1 credit) - [Async Jobs](http://localhost:3000/docs/endpoints/jobs): `POST /v1/jobs/` — Queue research, crawl, batch or multi-extract work; poll or get a webhook. (5 credits / job (research 8 · crawl 5 · batch 3 · multi-extract 4)) - [Change Monitor](http://localhost:3000/docs/endpoints/change-monitor): `POST /v1/change-monitor/` — Snapshot a page and report added, removed and changed content since last check. (2 credits) - [Knowledge Lookup](http://localhost:3000/docs/endpoints/knowledge): `GET /v1/knowledge` — Look up an entity in the knowledge index by name. (1 credit) - [Enrich](http://localhost:3000/docs/endpoints/knowledge): `POST /v1/enrich` — Build a structured entity record from a name, URL or text. (4 credits) - [MCP Server](http://localhost:3000/docs/endpoints/mcp): `POST /v1/mcp/` — Every capability as Model Context Protocol tools over JSON-RPC. (billed per tool call) ## Optional - [Quickstart](http://localhost:3000/docs/getting-started/quickstart): first request in two minutes - [Credits](http://localhost:3000/docs/getting-started/credits): pricing and refunds - [Rate limits](http://localhost:3000/docs/getting-started/rate-limits) - [Webhooks](http://localhost:3000/docs/endpoints/webhooks): signed job callbacks - [Playground](http://localhost:3000/playground): try any endpoint in the browser - [Full reference with example bodies](http://localhost:3000/llms-full.txt)