> ## Documentation Index
> Fetch the complete documentation index at: https://docs.keenable.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Every page is listed in https://docs.keenable.ai/llms.txt. To pick a product for a job, read https://docs.keenable.ai/choose.md
> Setup steps for agents, covering the SDKs, the MCP server and the CLI: https://docs.keenable.ai/skill.md
> Keenable search and fetch work without an API key. To add them to code, use the official SDK for the project's language: https://docs.keenable.ai/sdks.md
> Without a key, call POST https://api.keenable.ai/v1/search/public or GET https://api.keenable.ai/v1/fetch/public with an X-Keenable-Title header that names your app.
> With a key, send it in the X-API-Key header and read it from the KEENABLE_API_KEY environment variable. Never ask a user to paste a key into chat. Every access method: https://docs.keenable.ai/auth.md
> To get an API key without the console, use device login: https://docs.keenable.ai/authentication.md#device-login
> MCP server: https://api.keenable.ai/mcp (no key, or X-API-Key; keyless Codex uses https://api.keenable.ai/mcp-public), or https://api.keenable.ai/mcp-oauth for OAuth sign-in. These docs are an MCP server at https://docs.keenable.ai/mcp and the OpenAPI spec is at https://docs.keenable.ai/api-reference/openapi.json
> Keenable searches and fetches public web pages. If a question needs no web information, skip the call.
> On 402 with an API key (code insufficient_credits), stop and ask a human to add credits; don't retry. On 429, wait the number of seconds in Retry-After, then retry. Before you ship, follow https://docs.keenable.ai/production.md
> Every error, with its cause and fix, is in https://docs.keenable.ai/errors.md and moving from another search API is covered in https://docs.keenable.ai/migrate.md
> Before you compare Keenable with another search API, read https://docs.keenable.ai/guides/evaluate-search-apis.md

# Keenable pricing

> Search and fetch are free without a key. With a key, you get 100,000 free requests a month, then pay $4 per 1,000. What each call costs and what isn't billed.

You can call search and fetch free without an API key, within the keyless rate limits. With an API key, your organization gets 100,000 free requests a month, worth \$400. After that, each request costs \$4 per 1,000, paid from a balance you top up in advance. An agent with no account can pay for each request instead.

## Ways to pay

| Way to pay | What it costs | Limits |
| - | - | - |
| No API key | Free | 1,000 requests per hour and 10 per second, per IP address, for each endpoint. See [rate limits](https://docs.keenable.ai/rate-limits.md). |
| API key, free allowance | Free for 100,000 requests a month | 10 requests per second per organization by default, no hourly cap. See [the free allowance](https://docs.keenable.ai/credits.md#monthly-allowance). |
| API key, prepaid balance | \$4 per 1,000 requests | 10 requests per second per organization by default, 25 after \$1,000 of top-ups in 90 days. See [rate limits](https://docs.keenable.ai/rate-limits.md#raise-your-limit). |
| [Pay per request](https://docs.keenable.ai/pay-per-request.md) (x402) | \$0.01 per search or fetch, \$0.10 per SELECT query, in USDC on Base | 50 paid requests per second per wallet, no hourly cap |
| [Prepaid balance through ZeroClick](https://docs.keenable.ai/pay-per-request.md#prepaid-credits-through-zeroclick) | \$4 per 1,000 searches or fetches, \$0.10 per SELECT query. A balance starts at \$0.50. | 50 requests per second per agent, no hourly cap |

These are standard rates. Your organization can have its own prices. Each keyed response reports what the call cost in `usage.credits`. A credit is \$0.004, so \$1 buys 250 credits and a \$4-per-1,000 call costs 1 credit. See [reading usage per call](https://docs.keenable.ai/credits.md#reading-usage-per-call).

Keenable uses the free allowance first, then your prepaid balance. The allowance resets each month, on the day of the month your organization was activated. A prepaid balance never expires.

If you sign up with an address from a disposable or privacy mail domain, such as Proton or Tuta, your organization starts with 1,000 free requests a month. Save a card in the console to get the full 100,000. Saving the card charges nothing.

## What each call costs

With an API key, each call is billed under a SKU that names what ran. A search is one request whether it returns 1 result or 50.

| SKU | Operation | Standard price |
| - | - | - |
| `search.pro` | A search served in `pro` mode | \$4 per 1,000 |
| `search.realtime` | A search served in `realtime` mode | \$4 per 1,000 |
| `fetch` | A fetch of Keenable's indexed copy of a page | \$4 per 1,000 |
| `fetch.live` | A fetch made live from the source | \$4 per 1,000 |

Your organization can have its own prices. The [Time Machine](https://docs.keenable.ai/api-reference/time-machine.md) endpoints, in Early Access, bill under their own SKUs. To see what a call cost, read `usage.credits` in the response. See [reading usage per call](https://docs.keenable.ai/credits.md#reading-usage-per-call).

The MCP server isn't billed separately. With an API key, its tool calls draw on the same balance at the same price as the HTTP API.

To turn your expected search and fetch volume into a monthly figure, see [Cost at volume](https://docs.keenable.ai/guides/cost-at-volume.md).

## Top up and auto top-up

Top up your balance under **Billing** in the [console](https://app.keenable.ai/console/billing). You need a card to top up, to turn on auto top-up, or to get the full allowance after a signup from a disposable or privacy mail domain.

If the allowance and your prepaid balance both run out, `/v1/search` and `/v1/fetch` return `402` until you top up or the allowance resets. To avoid the `402`, turn on [auto top-up](https://docs.keenable.ai/auto-top-up.md). When your prepaid balance falls below a threshold you set, Keenable charges your saved card and adds that amount.

## What isn't billed

These calls cost nothing:

| Call | Why |
| - | - |
| Calls without an API key | Keenable doesn't meter them. The [rate limits](https://docs.keenable.ai/rate-limits.md) cap them instead. |
| Failed calls | A failed call costs nothing. On the pay-per-request paths, a response of `400` or above is never charged. See [what is charged](https://docs.keenable.ai/pay-per-request.md#what-is-charged). |
| [Monitors](https://docs.keenable.ai/products/monitors) | Monitors is free for now. Monitors API requests, runs and webhook deliveries cost nothing. An organization can have up to 100 active monitors. |
| Pay-per-request calls | An x402 or ZeroClick call is paid for on its own. It never draws on your organization's allowance or balance. |

## Plans and volume pricing

Dedicated capacity costs \$1 per 1,000 requests at 100 or more requests per second, in the cloud or on-premises. Prices between \$4 and \$1 per 1,000 requests are quoted per organization.

See [Keenable pricing](https://keenable.ai/pricing) for the current plans. For a volume quote, [contact Keenable](https://keenable.ai/contact). To raise your rate limit, see [Raise your limit](https://docs.keenable.ai/rate-limits.md#raise-your-limit).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.