Capture pages without browser cleanup work.
Use separate scrape, screenshot, and parse endpoints. Screenshots remove cookie banners, overlays, and chat widgets, load lazy content, and stitch tall pages.
Page contentClean screenshotsDocuments
Turn the live webinto agent-ready data
Scrape pages, capture clean screenshots, parse documents, crawl sites, or extract structured data through focused endpoints.
One API, the whole path
Everything between a URL and usable data.
Use one focused platform for live web content, discovery, extraction, and company intelligence—without building browser fleets or brittle parsers.
Map and crawl entire sites.
Discover URLs from sitemaps and links, then run bounded crawls with depth controls, concurrency, deduplication, and webhooks.
URL discoveryAsync jobsWebhooks
Search the web, then read it.
Find current sources with advanced operators and bring the relevant page content back in the same workflow.
Live resultsSource contentAdvanced queries
Extract the shape you need.
Describe the data or provide a schema. Berrycrawl turns one page—or a list of pages—into structured JSON jobs.
JSON schemaAI extractionBatch URLs
Understand the company behind a URL.
Point to a company website and receive one clear brand profile: name, description, tagline, logos, images, colors, fonts, and socials.
Brand profileVisual identitySocials
Give agents a native connection.
Give a coding agent one prompt. It reads the docs, asks you to add one server-side API key, and wires the requested endpoint into your app.
Copy-paste promptServer envMCP
Built for products, not demos
Fresh web context where your workflow needs it.
berrycrawl is the infrastructure layer behind research, retrieval, enrichment, and asynchronous web-data jobs.
RAG pipelines
Keep retrieval grounded in the current web.
Map documentation, crawl every relevant page, and feed clean markdown into your index without maintaining browser infrastructure.
WorkflowReady
1/docs/quickstart
2/docs/api/auth
3/docs/sdk/typescript
Research agents
Search, verify, and cite real sources.
Give agents a compact sequence: find sources, scrape the useful pages, and extract the facts they need to reason.
WorkflowReady
1Search current sources
2Read primary pages
3Return structured facts
Brand enrichment
Turn a company website into a usable brand profile.
Send the website URL and receive its name, description, logos, colors, fonts, images, and social profiles.
WorkflowReady
1company.com
2Visual identity
3Brand profile ready
Change-aware workflows
Run large jobs without holding a connection open.
Start crawl and extraction jobs asynchronously, then track status or receive signed webhook deliveries.
WorkflowReady
1job.created
2page.completed
3crawl.completed
Agent-native setup
Connect it your way.
Use the dashboard yourself, or hand your coding agent one prompt and add one server-side environment variable.
Do it yourself
- 01Create a workspace and API key.
- 02Pick REST, MCP, or an SDK workflow.
- 03Send your first URL and inspect the result.
Let your agent do it
RecommendedPaste one prompt into your coding agent. It reads the repo, asks you to add a normal bearer key to the server environment, and wires the requested endpoint without seeing the secret.
Agent setup prompt
Paste this into your coding agent while it is open in the application repository.
Read https://berrycrawl.com/llms.txt and https://docs.berrycrawl.com/docs/guides/agent-quickstart, then integrate Berrycrawl into this repository.
First inspect the repository's language, framework, server entry points, package manager, existing environment files, and test commands. Do not ask me to paste a secret into chat. Tell me to create a Berrycrawl API key in the dashboard and add this variable to the server-side environment file or secret store:
BERRYCRAWL_API_KEY=bc_...
Wait until that variable exists in the environment you will use. Then implement the smallest server-side integration for the feature I asked for. Use the endpoint and request shape from the Berrycrawl docs, keep the key out of browser bundles and source control, add a focused test or local verification path, and report the files changed and the command I can run to verify it.
If the feature starts a crawl or extraction job, persist the returned id and poll GET https://api.berrycrawl.com/api/v1/jobs/{id} until the status is COMPLETED, FAILED, or CANCELLED. Do not create a second job when polling a known id.- 01
Choose the primitive
Scrape one page, map or crawl a site, search the web, extract a schema, or resolve a brand.
- 02
Connect once
Use a bearer key with REST, your preferred SDK workflow, or the stateless MCP endpoint.
- 03
Ship the feature
Return data synchronously or let webhooks carry crawl and extraction jobs to completion.
Straightforward pricing
Pay for the web work you actually run.
No subscription ladder and no expiring paid balance. Start small, top up when you need to, and unlock higher throughput as your usage grows.
Start free
100credits
A new workspace receives a one-time credit grant so you can try the real API before topping up.
- Up to 3 concurrent scrapes
- REST API and dashboard
- No credit card to create an account
Pay as you go
$1per 1,000 credits
Top up from $10. Paid credits do not expire, and cumulative spend raises your rate and concurrency tier.
- Flat launch rate
- No recurring subscription
- Up to 200 concurrent scrapes on automatic tiers
Build the feature.Skip the crawler project.
Start with 100 credits, a production API, and documentation that works for humans and agents.