> ## 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 guides for web search and fetch

> How-to guides for Keenable search and fetch: filters, operators, result size, fetch prompts, live and long pages, citations, keyless, volume and cost.

Each guide solves one task with Keenable search or fetch, with runnable code in Python, TypeScript, Go, Rust and curl, a real response, and the mistakes that return the wrong results. Every sample runs with no API key.

## Pick a guide

| Guide | What you get | Parameters it covers |
| - | - | - |
| [Filter by date](https://docs.keenable.ai/guides/filter-by-date) | Results from a date window, such as the last 7 days | `published_after`, `published_before`, `acquired_after`, `acquired_before` |
| [Filter by domain](https://docs.keenable.ai/guides/filter-by-domain.md) | Results from the sites you trust, without the ones you don't | `site`, `exclude_domains` |
| [Search, then fetch](https://docs.keenable.ai/guides/search-then-fetch.md) | The facts you need with the least text in your context | `snippet_max_length`, `prompt`, `max_chars`, `live` |
| [Choose a search mode](https://docs.keenable.ai/guides/choose-a-search-mode.md) | The right trade between depth and response time | `mode` |
| [Ground answers with citations](https://docs.keenable.ai/guides/ground-answers-with-citations.md) | Answers whose claims map to source URLs | `to_context()`, `cited()` |
| [Keyless access](https://docs.keenable.ai/guides/keyless-access.md) | Search and fetch before anyone creates an account | `/v1/search/public`, `X-Keenable-Title`, `/mcp-public` |
| [Search operators](https://docs.keenable.ai/guides/search-operators.md) | Exact phrases, several sites in one request, and exclusions | `"..."`, `site:`, `OR`, `-`, `( )` |
| [Result size](https://docs.keenable.ai/guides/result-size.md) | Search results sized to your context, without cards | `max_results`, `snippet_max_length`, `disable_cards` |
| [Fetch with a prompt](https://docs.keenable.ai/guides/fetch-with-prompt.md) | Only the facts you asked for from a page, in a format you can parse | `prompt` |
| [Live fetch](https://docs.keenable.ai/guides/live-fetch.md) | The current version of a page that changes often | `live` |
| [Long pages](https://docs.keenable.ai/guides/long-pages.md) | Long pages that don't fill your context | `max_chars`, `truncated`, `total_chars` |
| [High-volume research](https://docs.keenable.ai/guides/high-volume-research.md) | Many parallel calls without losing any to `429` | `Retry-After`, `max_retries`, `X-Keenable-Session-Id` |
| [Cost at volume](https://docs.keenable.ai/guides/cost-at-volume.md) | A monthly cost estimate from your search and fetch volume | `usage.credits`, free allowance, \$4 per 1,000 |
| [Docs lookup for coding agents](https://docs.keenable.ai/guides/docs-lookup-for-coding-agents.md) | A coding agent that checks current library docs before it writes code | `site`, `prompt`, `AGENTS.md` |

## Combine the filters

The filters from several guides work together in one request. This keyless request searches one GitHub organization for pages published in the last year, in `realtime` mode, and returns 3 short results:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
curl -X POST https://api.keenable.ai/v1/search/public \
  -H "Content-Type: application/json" \
  -H "X-Keenable-Title: My App" \
  -d '{
    "query": "release notes for a new Tokio version",
    "site": "github.com/tokio-rs",
    "published_after": "1y",
    "mode": "realtime",
    "max_results": 3,
    "snippet_max_length": 180
  }'
```

You see a search response whose `mode` is `realtime`, with 3 results on `github.com/tokio-rs`, each published in the last year:

```text Example output · results vary, mode and URLs shown theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
realtime
2026-09-08 https://github.com/tokio-rs/tokio/issues/8434
2026-05-04 https://github.com/tokio-rs/tokio/commit/f82bcf3f45eb9d0dad9d7e45251adf67223f03b6
2026-07-16 https://github.com/tokio-rs/tokio/commit/b0ba02e75507518baed6718b0c37105e430f3a93
```

## Related pages

* [Cookbook](https://docs.keenable.ai/cookbook.md): search and filter every guide and recipe.
* [Best practices](https://docs.keenable.ai/best-practices.md): query writing, parallel searches and context size.
* [Search](https://docs.keenable.ai/products/search.md) and [Fetch](https://docs.keenable.ai/products/fetch.md): cost and every key parameter.
* [Search API reference](https://docs.keenable.ai/api-reference/search.md): every request parameter and response field.


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