← Catalog

Web scraping API: any page into clean markdown for an LLM

web.scrape

live

Clean markdown of a page or site for agent context.

live coverage

Firecrawl: all inputs ✓

Apify: all inputs ✓

✓ marks a combination proven with a real provider call. Others are wired and unit-tested; their first live run verifies them.

Providers

ProviderStatus
Firecrawl live
Apify live

Billing

Unit: per_page · unmatched results billed: no

The exact quote is returned by /v1/inspect before every call and held with headroom on execution. The quote is the price floor: if the provider's actual cost overruns it, the run bills the overrun at the same rate, never above the hold. The unused part of every hold is released.

Run it

curl https://api.jell.run/v1/run \
  -H "Authorization: Bearer $JELL_API_KEY" \
  -d '{
    "capability": "web.scrape",
    "input": { "url": "..." },
    "routing": {"provider": "auto"}
  }'

Input schema

{
  "properties": {
    "url": {
      "type": "string"
    }
  },
  "required": [
    "url"
  ],
  "type": "object"
}

Normalized output fields

url · title · markdown

Used in these guides

Web scraping for agents: why one provider is not enough →Web search and scraping for agents →