Getting started
Account and API key
You need no account and no API key to search or fetch. If you send an API key, your organization gets its own limit of 10 requests per second with no hourly cap, and 100,000 free requests a month. Top-ups of $1,000 within 90 days raise that limit to 25 requests per second for 90 days. See Raise your limit. Responses to keyed calls also report what each call cost in ausage object. To add a key, see API keys.
Keyless billing and limits
Keyless requests are free. If you don’t send an API key, Keenable allows 1,000 requests per hour and 10 per second per IP address, counted separately for search and for fetch. All traffic from your IP address shares that pool, so other callers on your network reduce your headroom. See Rate limits.The index behind the results
Search and fetch run on Keenable’s own index. Each search result carriesacquired_at, the time Keenable indexed the page, so you can judge how fresh its snippet is. See the Search response. Keenable’s crawler, KeenableBot, builds the index. See Keenable crawlers.
Search, Fetch and SELECT
Search returns ranked web pages about a topic, each with text from the page insnippet. Fetch returns one page as markdown when you already have its URL. SELECT is a separate MCP server that needs a Keenable account: your agent writes one read-only SQL SELECT, and the server returns a table built from live web pages. Start with Search, Fetch or SELECT. To compare all five products side by side, see Choose a product.
Index crawling
Keenable crawls the web with its own crawler, KeenableBot, which collects public pages to build and maintain the Keenable search index. KeenableBot followsrobots.txt, so a site that blocks it no longer appears in Keenable search results. When a fetch reads a page live from its source, the request goes out as Keenable-User. See Keenable crawlers for the user agents and the IP lists that verify them.
Search and fetch
Search modes
Search has two modes.pro does deeper retrieval and is the mode a search runs in if you set none and your organization has no other default. realtime returns the fastest response, for latency-sensitive agent loops. Each mode is billed as its own SKU, and the response names the mode that served the call in mode. See the Search request.
Recent results and query_time
To get recent results, set published_after to a date, a timestamp or a relative delta such as 7d. The results then leave out pages with no known publish date. query_time isn’t a recency filter: it searches the index as it stood at that moment and sets no lower bound. See Date and time filters.
Card results
A card is a result that Keenable writes for queries such as prices, exchange rates or facts about a company. Itsurl starts with https://cards.keenable.ai/w/. To get ordinary web pages in place of cards, send disable_cards: true. You still get the same number of results. See the Search request.
Empty description field
The description field is deprecated and always an empty string. Read the page text from snippet on a search result and from content on a fetch response. See Versioning and deprecation.
Pages with no indexed copy, and live=true
By default, Fetch returns Keenable’s indexed copy of a page. If Keenable has no indexed copy, it fetches the page live from the source and bills the call as fetch.live, even if you didn’t send live=true. Send live=true when you need the current version of a page that changes often. See Fetch.
Keys, prices and limits
Cost of a call
Search and fetch each cost $4 per 1,000 requests, and every organization gets 100,000 free requests a month. Your organization can have its own prices, so readusage.credits in each keyed response to see what the call cost. One credit is $0.004. Keyless calls and failed calls report no usage. See Pricing and Balance and usage.
Out of funds
If you’ve used the monthly allowance and your prepaid balance is used up,/v1/search and /v1/fetch return 402 with the code insufficient_credits. The body’s billing_url links to the billing page. Top up your balance in the console, or wait for the allowance to reset. See Balance and usage.
Prepaid balance and auto top-up
Keenable uses your free requests first, so your prepaid balance goes down only once the monthly allowance is spent. Auto top-up is off until you turn it on in the console. Once it is on, Keenable charges your saved card the amount you set whenever the prepaid balance falls below your threshold, up to your monthly limit. See Auto top-up.429 and 402
Retry a 429, and don’t retry a 402. A 429 means you sent requests faster than your rate limit allows: wait for the time in the Retry-After header, then send the request again. A 402 means your organization is out of funds, and every retry returns the same 402 until someone tops up or the allowance resets. See Errors.
High request volumes
With an API key, your organization gets 10 requests per second with no hourly cap. The limit rises to 25 once your completed top-ups reach $1,000 within 90 days. For more than 25 requests per second, contact Keenable. Dedicated capacity, in the cloud or on-premises, is described under Plans and volume pricing. If you send calls in parallel, keep each batch under your per-second limit, and after a429 wait for Retry-After before you retry. See Raise your limit.
Zero data retention
Zero data retention (ZDR) is a data retention policy that Keenable sets for an organization as part of the Enterprise offer. The console has no switch for it: ask through Talk to us in the console, or use the contact form. The policy follows the API key, so send a key from the ZDR organization on every call. A keyless request isn’t under your organization’s policy. Under ZDR, a fetch with aprompt returns 400 with zdr_prompt_unsupported. On the default policy, Keenable logs every search and fetch request. See Zero data retention.
Connecting
SDK, MCP server, REST API or CLI
All five work without an API key. For a first search with each, see the Quickstart. To have your coding agent do the setup, use Copy setup prompt on the Quickstart.
Keyless calls over HTTP
To call the HTTP API without a key, send the request to the/public twin of the endpoint, such as /v1/search/public or /v1/fetch/public, with an X-Keenable-Title header that names your application. If the header is missing, the API returns 400 with Missing app identifier. If you can’t set a header, pass the same value in the ?keenable_title= query parameter. The MCP server at https://api.keenable.ai/mcp needs no key either. See API authentication.
Send a session ID from an SDK
No SDK has asession_id argument. Send the X-Keenable-Session-Id header through the client’s default headers (TypeScript from keenable 0.2.0). See Group a run with a session ID.
A client that keeps using its own web search
Turn off the client’s own web tools and add a routing rule, as Make Keenable the default web tool shows for Claude Code, Codex, Cursor and OpenCode.Paying per request without an account
An agent with a wallet can call search and fetch with no account and no API key on the/v1/x402/* paths. Each search or fetch costs $0.01 in USDC on Base, paid over the x402 protocol. If you call Keenable regularly, an API key costs less. See Pay per request.
Help and changes
Report a problem
Email support@keenable.ai about your account, billing or the API. Include theX-Request-Id header value from the response so Keenable can find your request in its logs. For a bug in an SDK or the CLI, open a GitHub issue in its repository. See Get help.
Breaking changes
Within/v1, Keenable ships only backward-compatible changes and announces them in the changelog. A deprecated endpoint, parameter, response field or MCP tool is announced in the changelog and by email to organization owners, and keeps working for at least 90 days after the announcement. Anything the docs mark as experimental can change without that notice. See Versioning and deprecation.