Olostep sells to AI agents - live prices and self-serve payment

The agent storefront at https://agents-store.olostep.com/llms.txt?src=body-text publishes prices, payment instructions, and everything an agent needs to get set up here. Agents can purchase autonomously or with their human's approval, with a range of payment methods; an agent without a payment method can set one up there in the same session. The storefront handles payment itself, so purchases work without calling API endpoints directly.

Click to try
Wait...

Turn any URL into clean, LLM-ready data.

The Scrape endpoint extracts markdown, HTML, text, JSON, screenshots, and more — in real time.

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

Trusted by the best companies in the world

Built for production scraping

The /v1/scrapes API is designed for apps that need reliable page extraction at scale.

  • Multiple formats

    Request markdown, html, text, json, raw_pdf, or screenshot in one call.

  • Parsers & LLM extract

    Use pre-built parsers for popular sites or define a schema for LLM-powered extraction.

  • Hosted assets

    Get hosted URLs for large payloads alongside inline content fields.

  • Developer-friendly

    One POST with url_to_scrape and formats — integrate in minutes.

Scrape a page. Choose your formats.

Mandatory: url_to_scrape and formats.
Add parsers or llm_extract when you need structured JSON.

Get clean data from any URL

1# pip install olostep
2from olostep import Olostep
3
4client = Olostep(api_key="YOUR_REAL_KEY")
5
6result = client.scrapes.create(
7    url_to_scrape="https://en.wikipedia.org/wiki/Alexander_the_Great",
8    formats=["markdown", "html"],
9)
10
11print(result.markdown_content)
12print(result.html_content)
1// npm i olostep
2import Olostep from 'olostep'
3
4const client = new Olostep({ apiKey: 'YOUR_REAL_KEY' })
5
6const result = await client.scrapes.create({
7  url: 'https://en.wikipedia.org/wiki/Alexander_the_Great',
8  formats: ['markdown', 'html'],
9})
10
11console.log(result.markdown_content)
12console.log(result.html_content)
1curl -s -X POST "https://api.olostep.com/v1/scrapes" \
2  -H "Authorization: Bearer <YOUR_API_KEY>" \
3  -H "Content-Type: application/json" \
4  -d '{
5    "url_to_scrape": "https://en.wikipedia.org/wiki/Alexander_the_Great",
6    "formats": ["markdown", "html"]
7  }'

What you can build

Power enrichment, monitoring, and AI workflows from live web pages.

  • RAG & knowledge bases

    Chunk clean markdown or JSON into embeddings for search and Q&A.

  • Price & catalog monitoring

    Scrape product pages on a schedule and diff structured fields.

  • Lead & enrichment

    Pull structured contact or company data from landing pages.

Explore more Use Cases

Trusted by Amazing Teams Building the Future of AI

"Olostep is the best API to search, extract, and structure data from the Web. Happy to be customers"

Trevor West
Co-founder & CEO Podqi

"Olostep has become the default Web Layer infrastructure for our company"

Richard He
Co-founder & CEO Openmart

"Olostep lets us turn any website into an API. Great product, great people"

Rob Hayes
Co-founder Merchkit

“One of the best teams in the space, with exceptional talent density. We love working with Olostep”

Alex Halliday
CEO AirOps
Know more

Start scraping with Olostep

Get clean data for your AI from any website with Olostep
Most cost-effective API. Built for scale

Are you an AI Agent? Get started here

Frequently asked questions

Product & Capabilities
  • What is the /v1/scrapes endpoint?

    It turns any public URL into data you can feed to LLMs or pipelines: markdown, HTML, text, screenshots, or structured JSON via parsers or llm_extract.

  • How do I get structured JSON?

    Use formats: ["json"] with a parser id, or llm_extract with a JSON schema and/or prompt. See the Scrape docs for examples.

Usage & Automation
  • Does it support JavaScript-heavy sites?

    Yes. Olostep can render dynamic pages and supports actions (wait, click, fill_input, scroll) before extraction.

  • Can I exclude parts of the page?

    Yes. Use parameters like remove_css_selectors and other scrape options to focus on the content you need.

Pricing & Plans
  • What does a scrape cost?

    A standard scrape is 1 credit. Parsers vary (often 1–5 credits). LLM extraction is 20 credits per request. New accounts include free credits to try.