AI Web Data Extractor – Any URL to JSON with Your Schema
Pricing
from $1.00 / 1,000 page-extracteds
Go to Apify Store
AI Web Data Extractor – Any URL to JSON with Your Schema
Pricing
from $1.00 / 1,000 page-extracteds
Either a JSON Schema object (type: object with properties), or a simple map of field name to a plain-English description, e.g. {"title": "Book title", "price": "Price as a number"}.
Optional guidance for the model, e.g. "Prices are in euros" or "Only extract products from the main listing".
Turn on for listing pages. The result becomes an array with one entry per matching item, each following your schema.
Which API your key belongs to. Anthropic uses the Messages API; OpenAI also covers any OpenAI-compatible endpoint via the base URL field.
Your own API key. It is stored encrypted, used only for this run's model calls and never written to the dataset. LLM usage is billed by your provider, not by this Actor.
Model name. Leave empty for a cheap, fast default (Anthropic: claude-haiku-5-5, OpenAI: gpt-4o-mini).
Optional. Override for OpenAI-compatible providers such as OpenRouter, e.g. https://openrouter.ai/api/v1.
Pages are cleaned to text and cut at this length to control model cost. Raise it for very long pages.
Reuse a previous result when the same page content, schema, instructions and model are seen again within this time. 0 disables the cache.
How many pages are processed in parallel. Lower it if your LLM provider rate-limits you.
