Skip to main content
Replace Tavily Search and Extract calls with Keenable’s POST /v1/search and GET /v1/fetch. This page maps each Tavily endpoint, parameter and response field to Keenable, 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 Tavily 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.

POST /v1/search

GET /v1/fetch

Response map

POST /v1/search

GET /v1/fetch

Before and after

This search asks both APIs for 3 results published in the past year. The Keenable request runs without a key.
The Keenable response has query, mode and up to 3 results. Each result has a title and a url, and usually a snippet and a published_at. Tavily’s date filters use the publish date or the last-updated date. Keenable’s published_after uses the publish date only.

No equivalent in Keenable

These Tavily features have no Keenable counterpart. Remove them from the request, or handle them in your own code as described.
  • include_answer: Keenable returns sources, not a generated answer. Pass the snippet text to your own model.
  • topic: Keenable has no news or finance topic. Describe the kind of page you want in query.
  • country: Keenable has no country or language targeting.
  • include_images: Search and fetch return no image lists.
  • auto_parameters: Set each Keenable parameter yourself.
Mapping checked on 2026-11-19 against docs.tavily.com/documentation/api-reference/endpoint/search, docs.tavily.com/documentation/api-reference/endpoint/extract.

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 3 titles and URLs, each from a page published in the past year. 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[].snippet where it read results[].content, and handles a result that has no snippet.
  4. Calls that used include_raw_content now call GET /v1/fetch for each URL they need in full.
  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 or /v1/fetch and send X-API-Key. The response gains a usage object. See API keys.

Common questions

Send the request to /v1/search/public or /v1/fetch/public with an X-Keenable-Title header and no key. Without a key, each endpoint allows 1,000 requests per hour and 10 per second per IP address. See Rate limits.
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.
A parameter Keenable doesn’t know returns 400 with code unknown_parameter. When the name is close to a Keenable one, did_you_mean names it: start_date maps to published_after, include_domains to site and search_depth to mode. See Errors.
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.