Sign in
Extract (Beta)

Extract

Extracts relevant content from specific web URLs.

post/v1beta/extract

Headers

parallel-betastring nullable

Request body

client_modelstring nullable

The model generating this request and consuming the results. Enables optimizations and tailors default settings for the model's capabilities.

objectivestring nullable

If provided, focuses extracted content on the specified search objective.

search_queriesstring[] nullable

If provided, focuses extracted content on the specified keyword search queries.

session_idstring nullable

Session identifier to track calls across separate search and extract calls, to be used as part of a larger task. Specifying it may give better contextual results for subsequent API calls.

urlsstring[] required

Example request

{
  "client_model": "claude-opus-4-7",
  "fetch_policy": {
    "max_age_seconds": 86400,
    "timeout_seconds": 60
  }
}

Response

Successful Response

extract_idstring required

Extract request ID, e.g. extract_cad0a6d2dec046bd95ae900527d880e7

Example response

{
  "usage": [
    {
      "count": 1,
      "name": "sku_search_additional_results"
    }
  ],
  "warnings": [
    {
      "type": "spec_validation_warning"
    }
  ]
}

Changes