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.

Free product extraction tool

Product Intelligence

Turn manufacturer or retailer product pages into a structured catalog — name, model, specs, price, and images.

Product Catalog Builder

Product catalog JSON

Input

Comma-separated. Best starting point for a catalog.

Output
Run the tool to see output here.
  • Product URLs
  • Spec extraction
  • Custom schema

Developer experience

Build product catalogs from the web.

Use the Scrapes endpoint with llm_extract to pull structured product specifications from manufacturer and retailer pages.

REST APIJSON outputAI extractionProduct specsCustom schemaBatch support
Read the docs
curl --request POST \
  --url https://api.olostep.com/v1/scrapes \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "url_to_scrape": "https://www.example.com/products/widget-pro",
    "formats": ["json"],
    "llm_extract": {
      "prompt": "Extract product name, manufacturer, model, price, specs, and images"
    },
    "country": "US"
  }'

Catalog rows from live product pages

Paste product URLs (or search terms) and Olostep extracts structured specs. In production this is /v1/scrapes with llm_extract.

  • Seed URLs

    Comma-separated product pages are the most reliable starting point.

  • Optional search terms

    Add manufacturer plus queries when you do not have every URL yet.

  • Your schema

    Define the fields you need: name, model, price, specs, images.

How it works

Each tool is designed around a direct job: provide the input, get a useful output, and move it into your workflow.

  • 1

    Add product URLs

    Paste one or more product pages. Add queries if needed.

  • 2

    Olostep extracts specs

    Each page is scraped and turned into structured JSON.

  • 3

    Build the catalog

    Copy the payload into a sheet, PIM, or batch job.

Built for practical workflows

These tools are small on purpose: they solve the conversion job quickly, then point teams toward the API path when the workflow becomes recurring or high volume.

  • PIM onboarding

    Seed a catalog from manufacturer pages.

  • Price comparison

    Extract price and spec fields from retailer URLs.

  • Assortment research

    Collect a competitor’s published SKUs.

Need this at scale?

Use POST /v1/scrapes with formats json and llm_extract. For many URLs, send them as a batch of scrapes.

Frequently asked questions

Product & Capabilities

  • URLs work best. Search terms are a fallback when you only have a manufacturer plus queries.

  • It works on public HTML product pages. Heavily blocked sites may need retries or a different URL.

  • Yes. Pass an output schema for the keys you want.

Usage & Automation

  • Production path is /v1/scrapes with llm_extract. The snippet on this page shows that payload.

  • Loop scrapes or use batches of product URLs.

  • No. Persist the JSON in your own store.

Pricing & Plans

  • The page UI is free to use. Live runs use the Olostep API configured for this site and may be rate limited.

  • Olostep is usage based. See pricing for current plan details and included credits.

  • New Olostep accounts include free credits so you can test extraction before scaling.