Extract

Renders the page (JS included) and returns JSON matching the schema YOU declare, so there is no guessing at field names.

$0.0100 per call POST /v1/tools/extract Runs a model

Call it

The first response is 402 with the exact price and every rail you can pay with. Pay, repeat the request with the proof, and you get the result.

curl -X POST https://api.glianalabs.com/v1/tools/extract \
  -H 'content-type: application/json' \
  -d '{"url":"https://example.com/product","schema":{"title":"the product name","price":{"type":"number","description":"listed price"},"in_stock":{"type":"boolean"}}}'

When to use it

schema is { field: "description" } or { field: { type, description } } with type one of string | number | boolean | string[] (default string); max 25 fields. Values are coerced to your declared types — a price reads as a number, and Indonesian thousands separators (249.000) are read as 249000. Anything the page does not state comes back null and is listed in `missing` rather than invented. Optional prompt adds one extra instruction. Long pages are truncated at 24000 characters and the response says so.

What it costs

$0.0100 per successful call — flat, with no plan, minimum or monthly fee. A call that fails validation is refused before it runs, so it is never charged.

Not sure this is the right endpoint? GET /v1/consult?intent=… is free and answers that.