Thunderbit

O que é Thunderbit?

Thunderbit is an AI web-data extraction product for sales, operations, e-commerce and developer workflows. In the Chrome extension, specify column names and data types, extract matching information and export the resulting table. Paid collection tools include linked-subpage scraping, pagination and bulk URLs.

The same extraction infrastructure also supports an API: Distill returns Markdown, while Extract uses a JSON Schema to return structured fields. Access and usage accounting depend on the selected interface and current offering.

O que Thunderbit pode fazer?

Describe the fields to collect

Set column names and data types in the extension instead of building CSS selectors. The AI identifies and organizes matching page data.

Collect details across pages

Use paid subpage scraping, pagination and bulk-URL collection to combine information from lists and linked pages.

Work with PDFs, images and screenshots

Extract contact fields from PDFs and images. For pages that are difficult to capture directly, the extension also accepts screenshots and other file uploads.

Format and export the table

Add summaries, categories or translations during extraction, then export to Excel, Google Sheets, Airtable or Notion, or copy the results into another application.

Retrieve content through the API

Distill turns a URL into Markdown; Extract takes a URL and JSON Schema for structured JSON or CSV. Asynchronous batch jobs support programmatic collection.

Casos de uso

“Organize prospect information”

Collect names, roles, company details and contact fields from directories or other accessible sources, then review them together in a spreadsheet.

“Compare product listings”

Gather visible product names, prices, sellers and listing details from marketplace pages into a comparison table.

“Prepare web context for AI applications”

Use Markdown distillation for a knowledge-base pipeline, or request specific structured fields for an application or data-enrichment workflow.

Perguntas frequentes

How do Free pages and credits relate?

The browser Free plan includes six pages per month, with a maximum of 30 credits per page. Credit consumption for extraction, subpage collection, and enrichment should be checked against the current plan and feature pricing.

Is the API free allowance the same?

The API and browser extension have separate access and usage accounting. Check the current API documentation and pricing for available allowances and the units consumed by each endpoint; do not apply the browser page allowance to API requests.

How is the yearly Starter plan billed?

The displayed yearly Starter option is USD 9 per month, billed yearly, with 5,000 credits supplied upfront for the year. This is a monthly equivalent rather than a monthly payment. Business plans have custom pricing and limits.

Which collection features require a paid plan?

Paid plans include pre-built scrapers, subpage scraping, bulk scraping, pagination and data enrichment. Starter includes up to five scheduled scrapers; Pro includes up to 25. These capabilities should not be assumed from the Free page allowance.

Where can I use the extracted data?

Export browser results to Excel, Google Sheets, Airtable or Notion, or copy and paste them elsewhere. For application workflows, the API provides Markdown or structured JSON/CSV rather than requiring a spreadsheet export.