Skip to main content
Replace Linkup /v1/search calls with Keenable’s POST /v1/search. This page maps depth, outputType and the other Linkup parameters and response fields to Keenable, lists what has no equivalent, and shows the same request on both APIs.

Migrate with your coding agent

Paste this prompt into your coding agent. Your agent reads this page as markdown and rewrites your calls. Your agent finishes by running one Keenable request and showing you the result. The prompt works with Claude Code, Cursor, Codex and any other agent that can read a URL.

What changes

Endpoint map

Parameter map

A parameter Keenable doesn’t list returns 400 with Unknown parameter(s), so remove Linkup parameters instead of sending them along. “Closest” means the Keenable parameter does a similar job with a different format or behavior, described in the notes.

Response map

Before and after

This search asks both APIs for 5 pages published since 1 January 2025. The Keenable request runs without a key.
The Keenable response has query, mode and up to 5 results. Each result has a title and a url, and usually a snippet and a published_at. Read title where you read name, and snippet where you read content.

No equivalent in Keenable

These Linkup features have no Keenable counterpart. Remove them from the request, or handle them in your own code as described.
  • outputType: sourcedAnswer: Keenable returns sources, not a generated answer. Pass the snippet text to your own model and cite each url.
  • outputType: structured: Keenable returns no structured output, with or without includeSources. Pass the snippets to your own model with your JSON schema, and read sources from results.
  • includeImages: Search returns web pages only, with no image results.
Mapping checked on 2026-11-19 against docs.linkup.so/pages/documentation/endpoints/search/reference.md.

Use an SDK

This program sends the same search as the Keenable tab above with the official SDK. It runs without a key and prints the title and URL of each result.
You see up to 5 titles and URLs, each from a page published since 1 January 2025. Install the SDK for your language from SDKs.

Verify the migration

Check each item before you remove the old client:
  1. Run the Keenable request from Before and after. The status is 200.
  2. results has at most as many entries as max_results. Each entry has a title and a url.
  3. Your code reads results[].title where it read name, and results[].snippet where it read content, and handles a result that has no snippet.
  4. Calls that used sourcedAnswer or structured now pass the snippets to your own model.
  5. Your requests send no parameter from a None row. A leftover one returns 400 with unknown_parameter.
  6. Change the path to /v1/search and send X-API-Key. The response gains a usage object. See API keys.

Common questions

Send the request to /v1/search/public with an X-Keenable-Title header and no key. Without a key, the endpoint allows 1,000 requests per hour and 10 per second per IP address. See Rate limits.
Leave mode out to get pro, the default, for calls that used fast, standard or deep. Set mode to realtime for calls that used flash. Each mode is billed as its own SKU. See Search.
Keenable returns sources and has no answer field. Pass each result’s snippet to your own model and ask it to answer with citations to the url values.
Each result’s snippet holds page text, capped by snippet_max_length, up to 10000 characters. For the whole page, call GET /v1/fetch with the result’s url. See Fetch.
Each search mode and each kind of fetch is billed as its own SKU, and a call made with a key returns what it cost in usage. See Pricing and Balance and usage.