Text Extraction API
Turn any URL into clean plain text for NLP, search indexing and classification. No tags, no scripts, no parser to write.
{
"url": "example.com",
"format": "text-llm"
}- Output
- Plain text
- Cost
- From 0.25 credits a page
- Best for
- NLP and search indexing
- 500 free credits every month
- No card to start
- Failed requests cost nothing
Try it on your own URL






HTML isn't text
- Markup, scripts and styles are noise to an NLP or search pipeline
- Stripping it yourself means writing and maintaining a parser
- Nav bars, ads and footers leak into your word counts and embeddings
Clean plain text
The leanest formattextreturns the page as raw text, in far fewer tokens than raw HTMLtext-llmalso strips nav and boilerplate, for fewer tokens still- No parser to write or maintain — one request, words back
There is no separate endpoint to learn. Set format: "text" — or "text-llm" — on the Web Scraping API.
Words, and nothing else.
Everything that isn't prose is removed before the response, so nothing downstream has to know that the source was a webpage.
No markup at all
Tags, scripts, styles and inline attributes are gone. What you get is readable text.
format: "text"Boilerplate stripped
text-llm drops navigation, ads, footers and sidebars, leaving the primary content of the page.
format: "text-llm"Lowest token cost
Text carries no syntax overhead, so the same page costs fewer tokens than Markdown or HTML.
text-llmReady to tokenise
Feed it into embeddings, classification or sentiment analysis without a cleaning step first.
NLP-readySearch indexing
Index page content without teaching your indexer to ignore navigation that appears on every page.
full-textRenders first
JavaScript-rendered pages are loaded in a browser before extraction, so client-side content is included.
renderJSHow teams run text extraction at volume.
Keep the per-document token bill predictable
When every page goes through a model, the format decides the bill. Text carries no syntax at all, so the same page costs a fraction of what raw HTML would, and a long page is far less likely to blow the context window.
- Far fewer tokens than raw HTML with text-llm
- Predictable cost per document
- Nothing to strip before tokenising
POST /webscraping
{
"url": "https://www.twilio.com/docs/usage",
"format": ["text-llm"]
}One request, plain text back.
# pip install geekflare-api
from geekflare_api.client import GeekflareClient
from geekflare_api.models import WebScrapeDto
with GeekflareClient(api_key="<api-key>") as client:
result = client.web_scrape(
WebScrapeDto(
url="https://example.com",
format=["markdown"]
)
)
print(result)One API. Every stack.
One account works from an agent, a workflow builder, an SDK or your own service.
MCP server
Sign in once and Claude, ChatGPT, Cursor or Codex can use Geekflare's tools directly, with no glue code to write.
LLM & agent pipelines
LLM-ready Markdown straight into a retrieval pipeline, with the boilerplate stripped so you spend context on content, not navigation.
Workflow builders
Run any endpoint as a step in a visual scenario. Useful when the person who needs the data does not write code.
SDKs & REST
First-party typed SDKs for Python and Node. Everything else talks plain REST, from any language.
How many pages each plan covers.
Every format costs the same. A page is charged for what it needed, and failed requests cost nothing.
| Covered per month | Free $0/mo No card | Starter $19/mo | Most popular Growth $69/mo | Business 500K $299/mo | Business 1M $499/mo |
|---|---|---|---|---|---|
Credits a month | 500 | 20,000 | 100,000 | 500,000 | 1,000,000 |
Pages without a browserStatic pages that load without JavaScript rendering.0.25 credits | 2,000 | 80,000 | 400,000 | 2,000,000 | 4,000,000 |
Pages with JavaScriptRendered in a browser, with a basic proxy and stealth mode when needed.1 credit | 500 | 20,000 | 100,000 | 500,000 | 1,000,000 |
Pages with a premium proxyFor pages that block everything else, or when you pick a country.5 credits | – | 4,000 | 20,000 | 100,000 | 200,000 |
| Requests per second | 1 | 5 | 10 | 25 | 25 |
- Free$0/moNo card
- Credits a month
- 500
- Pages without a browser0.25 credits
- 2,000
- Pages with JavaScript1 credit
- 500
- Pages with a premium proxy5 credits
- –
- Requests per second
- 1
- Starter$19/mo
- Credits a month
- 20,000
- Pages without a browser0.25 credits
- 80,000
- Pages with JavaScript1 credit
- 20,000
- Pages with a premium proxy5 credits
- 4,000
- Requests per second
- 5
- GrowthMost popular$69/mo
- Credits a month
- 100,000
- Pages without a browser0.25 credits
- 400,000
- Pages with JavaScript1 credit
- 100,000
- Pages with a premium proxy5 credits
- 20,000
- Requests per second
- 10
- Business 500K$299/mo
- Credits a month
- 500,000
- Pages without a browser0.25 credits
- 2,000,000
- Pages with JavaScript1 credit
- 500,000
- Pages with a premium proxy5 credits
- 100,000
- Requests per second
- 25
- Business 1M$499/mo
- Credits a month
- 1,000,000
- Pages without a browser0.25 credits
- 4,000,000
- Pages with JavaScript1 credit
- 1,000,000
- Pages with a premium proxy5 credits
- 200,000
- Requests per second
- 25
What customers say.
“Found Geekflare API to get markdown from URL for my AI agents. It is fast and cheaper and works on almost every website.”
Ram DasiArchitect, PA Consulting“After trying many scraping services, I selected Geekflare to scrape public directories. Mainly for two reasons - it is cheaper and fast.”
“Documentation was easy to follow. We were scraping dynamic pages within hours. Very reliable service.”
Plain text, specifically.
General scraping questions are answered on the Web Scraping API page.
Open the Web Scraping API pagetext returns the whole page as plain text. text-llm additionally strips navigation, ads, footers and other boilerplate, leaving the primary content.Plain text, on your first request.
Create a free account to try any URL in the playground and grab your API key. 500 credits a month, no card.