> ## 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

# OmniRoute web search and fetch with Keenable

> Route web search and page fetch through Keenable in the OmniRoute AI gateway with provider keenable-search. No key needed, in OmniRoute 3.8.54 and later.

*Search and fetch provider in OmniRoute*

Keenable is a search and page-fetch provider in [OmniRoute](https://github.com/cheaper-inference/OmniRoute), the self-hosted AI gateway. Name `keenable-search` in a request to OmniRoute's search or fetch endpoint and the gateway calls Keenable for you. It works without a Keenable API key.

→ [Search API in OmniRoute's API reference](https://github.com/cheaper-inference/OmniRoute/blob/main/docs/reference/API_REFERENCE.md)

## Install

Keenable ships in OmniRoute 3.8.54 and later. Install or update the gateway from npm, then start it:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
npm install -g omniroute
omniroute
```

The gateway and its dashboard listen on `localhost:20128`. Copy an OmniRoute API key from the dashboard's **Endpoints** page: every call below sends it as a bearer token.

## Search the web

Send a query to OmniRoute's `/v1/search` with `provider` set to `keenable-search`:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
curl http://localhost:20128/v1/search \
  -H "Authorization: Bearer $OMNIROUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "rust async runtime comparison", "provider": "keenable-search", "max_results": 5}'
```

OmniRoute returns its own search response, with the provider that answered. Each result's text comes from Keenable's `snippet` field, which carries page text, cut to 300 characters by OmniRoute.

## Fetch a page

The same provider name works on `/v1/web/fetch`. Keenable returns the page as Markdown:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
curl http://localhost:20128/v1/web/fetch \
  -H "Authorization: Bearer $OMNIROUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com", "provider": "keenable-search", "format": "markdown"}'
```

Keenable fetch accepts only `"format": "markdown"`. Any other format returns `400`. OmniRoute caps the content at 100,000 characters.

## How OmniRoute picks Keenable

| Request | What happens |
| - | - |
| `"provider": "keenable-search"` with no Keenable connection | OmniRoute calls Keenable's keyless endpoint, rate limited per IP. |
| `"provider": "keenable-search"` with a Keenable key saved in OmniRoute | OmniRoute sends the key in `X-API-Key` to the keyed endpoint. Calls use your organization's limits and are billed to its [monthly allowance, then its balance](https://docs.keenable.ai/credits.md). |
| No `provider` and no `model` | Auto-select. Keenable is `fallbackOnly`: it never displaces a configured paid provider, and on fetch it joins the automatic pool only when a key is configured. |
| `"model": "<combo>"` | A saved combo can list Keenable as one of its targets. |

`max_results` defaults to 5 for Keenable and goes up to 50. OmniRoute sends one `site` domain and a `published_after` date when the request asks for them.

> [!NOTE]
>
> Without a key, searches run on the shared public tier at [lower rate limits](https://docs.keenable.ai/rate-limits.md). Save a Keenable API key in OmniRoute's provider settings to use your organization's limits. See [API keys](https://docs.keenable.ai/api-keys.md).

## Related pages

> [card] [Baseten](https://docs.keenable.ai/integrations/baseten.md)
>
> Keenable web search and page fetch as server-side tools on Baseten Model APIs, called by the model inside the inference loop.

> [card] [Cerebras](https://docs.keenable.ai/integrations/cerebras.md)
>
> Ground Cerebras Inference models in live web results with the Keenable SDK: one search for cited answers, or tool calling with TOOLS, in Python and Node.

> [card] [OpenRouter](https://docs.keenable.ai/integrations/openrouter.md)
>
> Web search and page fetch for any OpenRouter model, as tools it calls itself: from Python, the AI SDK, or the Agent SDK over MCP. No Keenable key needed.

> [card] [Overview](https://docs.keenable.ai/sdks.md)
>
> Install the official Keenable SDK for Python, TypeScript, Go or Rust with one command, search with no key, then add fetch, tool calling and Monitors.


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