Web pages as clean Markdown for your app and your agent
Turn a web page into Markdown, HTML or links, map the links of a site, or crawl a few pages, through one API key, with robots rules honoured.
Prepaid, never billed after
Reference
Galon Search is a web reading API that turns a page into clean Markdown, HTML or links, maps the links of a site and crawls a bounded set of pages, with robots rules honoured.
Updated . Prices and limits are read from the served price list and the platform code when this page is built.
| Plan or model | Included | Price | Per unit |
|---|---|---|---|
| Pages read | Pay as you use | $0.741 per 1,000 documents | — |
| Calls | Pay as you use | $0.741 per 1,000 requests | — |
| Limit | Value |
|---|---|
| Crawl pages (default limit) | 10 |
| Crawl pages (maximum per job) | 100 |
| Crawl depth (maximum) | 5 |
| Map links (maximum) | 1,000 |
| Page size (bytes) | 5 MiB |
| Results kept (hours) | 24 |
| Concurrent crawl jobs per project | 2 |
| Pages per site per day (default) | 500 |
| Site reading requests per minute per key (default) | 60 |
| Page timeout (milliseconds, maximum) | 60,000 |
| Indexes per project (default) | 10 |
| Documents per index (default) | 100,000 |
| Documents per account (default) | 500,000 |
| Document size | 64 KiB |
| Documents per batch | 1,000 |
| Queries per second per key (default) | 20 |
What you get
Pages your agent can read
- Scrape A URL into Markdown, HTML, raw HTML or its links
- Map The links a site exposes
- Crawl A bounded set of pages from a starting URL, as a job you can follow or cancel
- Polite by design robots.txt honoured, one request a second per host
- Results kept 24 hours Fetch them when your job is done
Get started
Three steps
- Create your accountFree, no card
- Copy your MCP configPaste it into your AI assistant
- Scrape a pageMap a site, crawl it
- Works through MCP, CLI or API
- Prepaid, never billed after
- Your cap, alert at 75%
curl -X POST https://api.galon.ai/v1/search/v2/scrape \
-H "Authorization: Bearer gln_test_••••" \
-H "Content-Type: application/json" \
-d '{"url": "https://akwaba.coffee/menu", "formats": ["markdown", "links"]}'curl -X POST https://api.galon.ai/v1/search/v2/map \
-H "Authorization: Bearer gln_test_••••" \
-H "Content-Type: application/json" \
-d '{"url": "https://akwaba.coffee"}'curl -X POST https://api.galon.ai/v1/search/v2/crawl \ -H "Authorization: Bearer gln_test_••••" \ -H "Content-Type: application/json" \ -d '{"url": "https://akwaba.coffee", "limit": 20}' # follow the job, results kept 24 hours curl https://api.galon.ai/v1/search/v2/crawl/{crawl_id} \ -H "Authorization: Bearer gln_test_••••"
Pricing
Prepaid, pay as you use
Pages read
$0.741 per 1,000 documents
Calls
$0.741 per 1,000 requests
- No card to start
- At $0, paid actions pause and your data is kept 30 days
- Every cost reserved before the action runs
- 1% of our revenue funds carbon removal through Stripe Climate.
Prices are paid from your prepaid balance. Top-ups are sold through our payment partner, which issues your receipt; domain names are sold separately.
Questions
Straight answers
- How much does Galon Search cost?
- Pages read are priced per 1,000 documents and calls per 1,000 requests, from $0.741 per 1,000 documents, paid from your prepaid balance.
- Does Galon Search render JavaScript?
- No. It fetches the HTML the server returns; JavaScript rendering and screenshots are not offered.
- Does it respect robots.txt?
- Yes, and it fetches each host at most once a second.
- How many pages can a crawl read?
- 10 pages by default and up to 100 per job, at a depth of 5 at most.
- How long are results kept?
- 24 hours. Fetch them when your job is done.
- Does Galon cap my spending?
- Galon sets no hard spending cap; you set your own.
Also on Galon Cloud
- MailTransactional email your agent can send by itself
- Mail ProProfessional mailboxes on your own domain
- DeployFrom a commit to a live address, driven by your agent
- AIAI models behind one key, with a cap you set
- StorageFiles for your app, uploaded straight to storage
- DomainsDomain names your agent can check and quote
- BackendA PostgreSQL database with migrations and backups
- FunctionsSmall JavaScript functions, isolated and bounded
- GeoMaps data for your app, behind one key
- ComputeIsolated compute for your workloads