Official Crawl4AI Cloud: a hosted web scraping, extraction, and search API for AI agents. Free API key, 1,000 credits a month, no card. Fully open source: this repo is the Apache-2.0 crawler that powers it, and you can self-host it.
Python aiai-agentscrawl4ai-cloudcrawlerdata-extractionllmmarkdownmcpopen-sourceplaywrightpythonragscraperweb-crawlerweb-crawlingweb-scraping
Cloud: one line for the five services and the two paces in the README, the docs home and the docs banner
unclecodeaadd82bebf98
diff --git a/README.md b/README.mdindex 0c340ab1..4ab11315 100644--- a/README.md+++ b/README.md@@ -21,7 +21,7 @@</div>-Crawl4AI turns any website into clean, LLM-ready Markdown for RAG, AI agents and data pipelines. Run the open-source web crawler and scraper yourself, free forever, or use it hosted with one key: scrape, search and extract through one API, with MCP for your agent.+Crawl4AI turns any website into clean, LLM-ready Markdown for RAG, AI agents and data pipelines. Run the open-source web crawler and scraper yourself, free forever, or use it hosted with one key: `/scrape` a page to Markdown, `/extract` it to JSON, `/search` the web, `/serp` for Google's results page as data, `/answer` a question with sources; MCP for your agent. Free: 10 a minute, 2 at a time, 2,000 credits to start. Paid: 120 a minute, 10 at a time, from $10.## Two ways to use Crawl4AI@@ -48,7 +48,7 @@ Docker server, CLI and every option: [Installation](#installation) · [docs.craw### ☁️ Or use the cloud: no browsers, no proxies-1. [](https://crawl4ai.com/?ref=readme)+1. [](https://crawl4ai.com/?ref=readme)Verify your email and free credit to start is yours. No card. Soft launch: prices can change, what you buy stays yours.2. Get any page as Markdown:@@ -59,7 +59,7 @@ Docker server, CLI and every option: [Installation](#installation) · [docs.craw-d '{"url": "https://news.ycombinator.com"}' | jq -r .markdown```- The same key works for `/search`, `/answer`, `/extract` and many URLs at once (`/scrape/batch`, `/scrape/jobs`). Pay as you go: [live prices](https://crawl4ai.com/docs?ref=readme#pricing).+ The same key works for `/extract`, `/search`, `/serp`, `/answer` and many URLs at once (`/scrape/batch`, `/scrape/jobs`). Pay as you go: [live prices](https://crawl4ai.com/docs?ref=readme#pricing).3. Give it to your AI agent. Claude Code shown; [Codex, Cursor and OpenCode →](https://crawl4ai.com/docs?ref=readme#mcp)```bash@@ -73,7 +73,7 @@ Docker server, CLI and every option: [Installation](#installation) · [docs.craw|---|---|---|---|| **Runs the browsers** | you, in your Python process | you, in Docker on your machine | we do || **JS-heavy pages and bot walls** | your settings, your proxies | your settings, your proxies | handled for you, automatically |-| **Web search** | – | – | `/search` and `/answer` |+| **Web search** | – | – | `/search`, `/serp` and `/answer` || **Price** | free, forever | free (your hosting) | pay as you go; free credit to start |<details>@@ -168,6 +168,7 @@ That platform is live now: [Crawl4AI Cloud](https://crawl4ai.com/?ref=readme).<summary>☁️ <strong>What the cloud adds</strong></summary>- 🔍 **Web search API**: `GET /search`, browser-free, ranked and cleaned. [Docs →](https://crawl4ai.com/docs?ref=readme#search)+- 📊 **SERP API**: `GET /serp`, Google's results page as data: true ranks, every block, localised to a place. Beta. [Docs →](https://crawl4ai.com/docs?ref=readme#serp)- 💬 **Answers**: `GET /answer` gives a direct answer to a question (experimental). [Docs →](https://crawl4ai.com/docs?ref=readme#answer)- 🧪 **Extraction without your own LLM key**: `POST /extract`. [Docs →](https://crawl4ai.com/docs?ref=readme#extract)- 🧗 **JS-heavy pages and bot walls**: handled automatically; you never pick an engine. [Docs →](https://crawl4ai.com/docs?ref=readme#scrape)diff --git a/docs/md_v2/index.md b/docs/md_v2/index.mdindex 2a437d60..92c0e49c 100644--- a/docs/md_v2/index.md+++ b/docs/md_v2/index.md@@ -55,7 +55,7 @@</div>-Crawl4AI turns any website into clean, LLM-ready Markdown for RAG, AI agents and data pipelines. Run the open-source web crawler and scraper yourself, free forever, or use it hosted with one key: scrape, search and extract through one API, with MCP for your agent.+Crawl4AI turns any website into clean, LLM-ready Markdown for RAG, AI agents and data pipelines. Run the open-source web crawler and scraper yourself, free forever, or use it hosted with one key: `/scrape` a page to Markdown, `/extract` it to JSON, `/search` the web, `/serp` for Google's results page as data, `/answer` a question with sources; MCP for your agent. Free: 10 a minute, 2 at a time, 2,000 credits to start. Paid: 120 a minute, 10 at a time, from $10.## Two ways to use Crawl4AI@@ -82,7 +82,7 @@ Docker server, CLI and every option: [Installation](core/installation.md) · [Se### ☁️ Or use the cloud: no browsers, no proxies-1. [](https://crawl4ai.com/?ref=docs)+1. [](https://crawl4ai.com/?ref=docs)Verify your email and free credit to start is yours. No card. Soft launch: prices can change, what you buy stays yours.2. Get any page as Markdown:@@ -93,7 +93,7 @@ Docker server, CLI and every option: [Installation](core/installation.md) · [Se-d '{"url": "https://news.ycombinator.com"}' | jq -r .markdown```- The same key works for `/search`, `/answer`, `/extract` and many URLs at once (`/scrape/batch`, `/scrape/jobs`). Pay as you go: [live prices](https://crawl4ai.com/docs?ref=docs#pricing).+ The same key works for `/extract`, `/search`, `/serp`, `/answer` and many URLs at once (`/scrape/batch`, `/scrape/jobs`). Pay as you go: [live prices](https://crawl4ai.com/docs?ref=docs#pricing).3. Give it to your AI agent. Claude Code shown; [Codex, Cursor and OpenCode →](https://crawl4ai.com/docs?ref=docs#mcp)```bash@@ -107,7 +107,7 @@ Docker server, CLI and every option: [Installation](core/installation.md) · [Se|---|---|---|---|| **Runs the browsers** | you, in your Python process | you, in Docker on your machine | we do || **JS-heavy pages and bot walls** | your settings, your proxies | your settings, your proxies | handled for you, automatically |-| **Web search** | – | – | `/search` and `/answer` |+| **Web search** | – | – | `/search`, `/serp` and `/answer` || **Price** | free, forever | free (your hosting) | pay as you go; free credit to start |## 🆕 AI Assistant Skill Now Available!diff --git a/docs/md_v2/overrides/partials/cloud-banner.html b/docs/md_v2/overrides/partials/cloud-banner.htmlindex 9812fe3b..339e295e 100644--- a/docs/md_v2/overrides/partials/cloud-banner.html+++ b/docs/md_v2/overrides/partials/cloud-banner.html@@ -10,7 +10,7 @@<div class="c4b-text"><div class="c4b-eyebrow"><span class="c4b-tag">New</span> good news for everyone who runs Crawl4AI</div><h2 class="c4b-title">Crawl4AI <em>Cloud</em> is live.<br>The same crawler, hosted.</h2>- <p class="c4b-lead">No browsers to run, no proxies to buy, no cookies to babysit. One key with <b>free credit to start</b>, and your AI agent can <b>search, scrape, crawl and extract</b> the web through the same engine you already use.</p>+ <p class="c4b-lead">No browsers to run, no proxies to buy, no cookies to babysit. One key with <b>free credit to start</b>, and your AI agent can <b>scrape, extract, search, read Google's results page (SERP) and answer questions</b> through the same engine you already use. Free: 10 a minute, 2 at a time, 2,000 credits to start. Paid: 120 a minute, 10 at a time, from $10.</p><p class="c4b-oss"><b>Always open source, forever.</b> The library stays here and stays free. The cloud is for the days you want to build fast and let us run the infrastructure.</p><div class="c4b-cta"><a class="c4b-btn" href="https://crawl4ai.com/?ref=docs-banner" data-c4b-ev="banner_key_clicked">Get a key, free credit to start →</a>