Skip to main content
This guide helps you migrate from the Beta Extract API (/v1beta) to the GA version (/v1).
Both the Beta and V1 APIs continue to be supported. Using the Beta API will result in warnings and no breaking errors in production until at least June 2026. We recommend migrating to the V1 API for the latest features and improvements.

​
Highlights

  1. Excerpts are always returned — The top-level excerpts field (bool or settings object) is removed. Excerpts are now always returned in the response; size is controlled via advanced_settings.excerpt_settings.max_chars_per_result. You can no longer disable excerpts by setting excerpts: false.
  2. Settings reorganized under advanced_settings — fetch_policy, excerpt settings, and full_content are now nested under a single new advanced_settings wrapper object (previously top-level fields). See Advanced Settings for the full list.
  3. Larger request capacity — urls now accepts up to 20 URLs per request, and objective now accepts up to 5000 characters.

​
Overview of Changes

ComponentBetaV1
Endpoint/v1beta/extract/v1/extract
SDK methodclient.beta.extract()client.extract()
urls limitUp to 10 URLs per requestUp to 20 URLs per request
objective limitUp to 3000 charactersUp to 5000 characters
ExcerptsConfigurable via top-level excerpts (bool or object); can be disabled with excerpts: falseAlways returned; size controlled via advanced_settings.excerpt_settings.max_chars_per_result (cannot be disabled)
max_chars_totalInside excerpts objectPromoted to top-level request field (controls total excerpt size; does not affect full_content)
client_model (new)—Top-level field for model-specific optimizations
session_id (new)—Top-level field for grouping related Search and Extract calls made by an agent as part of the same task. Server returns one on every response if not provided.
advanced_settings—New object nesting fetch_policy, excerpt_settings, and full_content

​
Migration Example

​
Before (Beta)

curl https://api.parallel.ai/v1beta/extract \
  -H "Content-Type: application/json" \
  -H "x-api-key: $PARALLEL_API_KEY" \
  -d '{
    "urls": ["https://www.un.org/en/about-us/history-of-the-un"],
    "objective": "When was the United Nations established?",
    "excerpts": {
      "max_chars_per_result": 5000,
      "max_chars_total": 50000
    },
    "full_content": {
      "max_chars_per_result": 50000
    }
  }'

​
After (v1)

curl https://api.parallel.ai/v1/extract \
  -H "Content-Type: application/json" \
  -H "x-api-key: $PARALLEL_API_KEY" \
  -d '{
    "urls": ["https://www.un.org/en/about-us/history-of-the-un"],
    "objective": "When was the United Nations established?",
    "max_chars_total": 50000,
    "advanced_settings": {
      "excerpt_settings": {
        "max_chars_per_result": 5000
      },
      "full_content": {
        "max_chars_per_result": 50000
      }
    }
  }'

​
Additional Resources

Questions? Contact support@parallel.ai.