> ## 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

# Data and privacy

> What Keenable logs from your search and fetch requests, how long the policies let it keep data, how zero data retention works, and who to contact.

Keenable logs and stores the content of search and fetch requests: the search query, the fetched URL, any fetch prompt, and the results. This applies to keyless requests and to accounts on the default data policy. Don't send secrets or personal data in a query, a URL or a prompt. For how Keenable handles API keys and applies zero data retention to an organization, see [Security and privacy](https://docs.keenable.ai/security.md).

## What each request log holds

Every search and fetch request on the default data policy is logged, whether or not you send an API key.

| Field | Logged | Notes |
| - | - | - |
| Search query | Yes | The `query` you send to search. |
| Fetched URL and `prompt` | Yes | The `url` and any `prompt` you send to fetch. |
| Results | Yes | The search results or the fetched content. |
| IP address and user agent | Yes | For keyed and keyless requests alike. |
| `X-Keenable-Title` | If you send it | The keyless `/public` paths require it. See [Try it without a key](https://docs.keenable.ai/authentication.md#try-it-without-a-key). |
| Request ID | Yes | The value the response returns in `X-Request-Id`. |
| Organization and key ID | If you send an API key | The ID of the key, not the key itself. |

SELECT also stores the output of each query as a result set that later queries can read. See [Result sets](https://docs.keenable.ai/select.md#result-sets).

## Retention

The Privacy Policy and the Terms of Service set no fixed retention period for request logs. [Retention and use](https://docs.keenable.ai/security.md#retention-and-use) on the security page says what each document allows for personal information and for the content you send.

## Zero data retention

Zero data retention (ZDR) is an Enterprise data policy that Keenable sets for an organization. It follows the organization that owns the API key, so a keyless `/public` request isn't under it. [Zero data retention](https://docs.keenable.ai/security.md#zero-data-retention) on the security page covers how the policy applies and the `400` errors it returns. To ask for it, see [Request other data terms](#request-other-data-terms).

### Check which policy applies to a key

Fetch a page with a `prompt`. A ZDR organization doesn't allow fetching with a prompt:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
curl -sS "https://api.keenable.ai/v1/fetch?url=https://example.com&prompt=Summarize+this+page" \
  -H "X-API-Key: $KEENABLE_API_KEY"
```

| Result | Policy |
| - | - |
| `400` with `"code": "zdr_prompt_unsupported"` | Zero data retention. Nothing is billed. |
| `200`, and `content` holds the answer to the prompt | The default policy. The call is billed as one fetch (see [Pricing](https://docs.keenable.ai/pricing.md)) and logged like any other request. |

To confirm your policy without a billed request, email [support@keenable.ai](mailto:support@keenable.ai) and name your organization.

## Policies

* The [Privacy Policy](https://keenable.ai/privacy) covers the personal information Keenable collects about you, such as your account and how you use the service, and how long Keenable keeps it.
* The [Terms of Service](https://keenable.ai/terms) cover your use of the API, the CLI, the SDKs and the MCP server.

If you're a business customer, the Privacy Policy doesn't cover the data Keenable processes on your behalf. To ask how Keenable handles that data, see [Request other data terms](#request-other-data-terms).

## Request other data terms

To ask about different data handling for your organization, including zero data retention, open [Talk to us](https://app.keenable.ai/console/talk-to-us) in the console and choose **Zero data retention**, use the [contact form](https://keenable.ai/contact), or email [support@keenable.ai](mailto:support@keenable.ai). For privacy questions, email [privacy@keenable.ai](mailto:privacy@keenable.ai).

Include the `X-Request-Id` value from a response when your question is about a specific request.


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