Sign in
Extract

Extract

Extracts relevant content from specific web URLs.

The legacy Extract API reference is available here.

post/v1/extract

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.

max_chars_totalinteger nullable

Upper bound on total characters across excerpts from all extracted results.

objectivestring nullable

As in SearchRequest, a natural-language description of the underlying question or goal driving the request. Used together with search_queries to focus excerpts on the most relevant content.

search_queriesstring[] nullable

Optional keyword search queries, as in SearchRequest. Used together with objective to focus excerpts on the most relevant content.

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

URLs to extract content from. Up to 20 URLs.

Example request

{
  "advanced_settings": {
    "fetch_policy": {
      "max_age_seconds": 86400,
      "timeout_seconds": 60
    }
  },
  "client_model": "claude-sonnet-4-6-20260401"
}

Response

Successful Response

extract_idstring required

Extract request ID, e.g. extract_cad0a6d2dec046bd95ae900527d880e7

session_idstring required

Session identifier. Echoed back from the request if provided, otherwise generated by the server. Should be passed to future search and extract calls made by the agent as part of the same larger task.

Example response

{
  "session_id": "session_8a911eb27c7a4afaa20d0d9dc98d07c0",
  "usage": [
    {
      "count": 1,
      "name": "sku_search_additional_results"
    }
  ],
  "warnings": [
    {
      "type": "spec_validation_warning"
    }
  ]
}

Changes