> ## 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

# Migrate to Keenable

> Switch from Tavily, Exa, Brave, Perplexity, SerpApi, Serper, Firecrawl, Parallel, Jina or Linkup to Keenable search and fetch, with mappings for each.

Replace another search API with Keenable by changing the request you send and the fields you read. Each provider below has its own page with endpoint, parameter and response maps, the same request on both APIs, and a prompt for your coding agent.

## What changes for every provider

| | Keenable |
| - | - |
| Base URL | `https://api.keenable.ai` |
| Auth with a key | `X-API-Key: $KEENABLE_API_KEY` on `/v1/search` and `/v1/fetch` |
| Auth without a key | No key on `/v1/search/public` and `/v1/fetch/public`. Send an `X-Keenable-Title` header with your app's name. |
| Search | `POST /v1/search` with a JSON body. Only `query` is required. |
| Page content | `GET /v1/fetch?url=...`, one URL per request. |
| Page text in search results | `results[].snippet`, in markdown. |

A list of domains to search and an exact-match flag become operators in the `query` string: `site:a.com OR site:b.com` and `"exact phrase"`. See [Search operators](https://docs.keenable.ai/api-reference/search.md#search-operators).

A parameter Keenable doesn't list returns `400` with `Unknown parameter(s)`, so remove the other provider's parameters instead of sending them along. When the other provider's name maps to a Keenable parameter, such as `count` or `limit` for `max_results`, the error's `did_you_mean` field names the parameter to use. See [Search](https://docs.keenable.ai/api-reference/search.md#request) and [Fetch](https://docs.keenable.ai/api-reference/fetch.md#request) for every parameter, and [Authentication](https://docs.keenable.ai/api-reference.md#authentication) for keys.

## Providers at a glance

Each row counts the provider's parameters on its page by how they map: exact, closest (a similar job with a different format or behavior), or none.

| Provider | Their endpoints | Keenable endpoints | Parameters: exact | Closest | None | Checked on |
| - | - | - | - | - | - | - |
| [Brave Search API](https://docs.keenable.ai/migrate/brave.md) | `GET /res/v1/web/search` | `POST /v1/search` | 2 | 3 | 8 | 2026-11-19 |
| [Exa](https://docs.keenable.ai/migrate/exa.md) | `POST /search`, `POST /contents` | `POST /v1/search`, `GET /v1/fetch` | 5 | 13 | 10 | 2026-11-19 |
| [Firecrawl](https://docs.keenable.ai/migrate/firecrawl.md) | `POST /v2/scrape`, `POST /v2/search` | `GET /v1/fetch`, `POST /v1/search` | 4 | 5 | 12 | 2026-11-19 |
| [Jina](https://docs.keenable.ai/migrate/jina.md) | `GET r.jina.ai/{url}`, `GET s.jina.ai/{q}` | `GET /v1/fetch`, `POST /v1/search` | 2 | 4 | 18 | 2026-11-19 |
| [Linkup](https://docs.keenable.ai/migrate/linkup.md) | `POST /v1/search` | `POST /v1/search` | 5 | 2 | 4 | 2026-11-19 |
| [Parallel](https://docs.keenable.ai/migrate/parallel.md) | `POST /v1/search`, `POST /v1/extract` | `POST /v1/search`, `GET /v1/fetch` | 5 | 8 | 5 | 2026-11-19 |
| [Perplexity Search API](https://docs.keenable.ai/migrate/perplexity.md) | `POST /search` | `POST /v1/search` | 2 | 5 | 3 | 2026-11-19 |
| [SerpApi and Serper](https://docs.keenable.ai/migrate/serpapi-serper.md) | `GET /search` (SerpApi), `POST /search` (Serper) | `POST /v1/search` | 2 | 2 | 8 | 2026-11-19 |
| [Tavily](https://docs.keenable.ai/migrate/tavily.md) | `POST /search`, `POST /extract` | `POST /v1/search`, `GET /v1/fetch` | 5 | 9 | 16 | 2026-11-19 |

## Tavily

Tavily Search maps to `POST /v1/search` and Tavily Extract to `GET /v1/fetch`. Keenable returns sources and has no generated `answer` field. See [Migrate from Tavily](https://docs.keenable.ai/migrate/tavily.md).

## Exa

Exa `/search` maps to `POST /v1/search` and `/contents` to `GET /v1/fetch`. Field names change from camelCase to snake\_case, and every search result carries a `snippet` without a `contents` object. See [Migrate from Exa](https://docs.keenable.ai/migrate/exa.md).

## Brave Search API

Brave web search, a `GET` with query parameters, maps to `POST /v1/search` with a JSON body. Results sit in a top-level `results` array instead of `web.results`. See [Migrate from the Brave Search API](https://docs.keenable.ai/migrate/brave.md).

## Perplexity

The Perplexity Search API's `POST /search` maps to `POST /v1/search`. Dates change from `MM/DD/YYYY` to `YYYY-MM-DD`. See [Migrate from the Perplexity Search API](https://docs.keenable.ai/migrate/perplexity.md).

## SerpApi and Serper

Google search through SerpApi or Serper maps to `POST /v1/search`. Read `results[].url` where you read `link`. See [Migrate from SerpApi or Serper](https://docs.keenable.ai/migrate/serpapi-serper.md).

## Firecrawl

Firecrawl `/scrape` maps to `GET /v1/fetch` and `/search` to `POST /v1/search`. Fetch returns the page as markdown in `content`. See [Migrate from Firecrawl](https://docs.keenable.ai/migrate/firecrawl.md).

## Parallel

Parallel Search maps to `POST /v1/search` and Extract to `GET /v1/fetch`. Settings under `advanced_settings` become top-level parameters. See [Migrate from Parallel](https://docs.keenable.ai/migrate/parallel.md).

## Jina Reader

Jina Reader's `r.jina.ai` maps to `GET /v1/fetch` and its search on `s.jina.ai` to `POST /v1/search`. Options sent as `X-` headers become query parameters or body fields, and the response is JSON with no `data` wrapper. See [Migrate from Jina Reader](https://docs.keenable.ai/migrate/jina.md).

## Linkup

Linkup `/v1/search` maps to `POST /v1/search`. `depth` becomes `mode`, and `outputType` goes away because Keenable always returns a `results` list. See [Migrate from Linkup](https://docs.keenable.ai/migrate/linkup.md).

## Bing Search API

Microsoft retired the Bing Search APIs on 11 August 2025, according to its [retirement notice](https://learn.microsoft.com/en-us/lifecycle/announcements/bing-search-api-retirement). To move code that called Bing web search, send the search text as `query` to `POST /v1/search` and read `results[].title`, `results[].url` and `results[].snippet`. Start from [Search](https://docs.keenable.ai/products/search.md).

## Verify the migration

Run one search without a key:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
curl -X POST "https://api.keenable.ai/v1/search/public" \
  -H "X-Keenable-Title: My App" \
  -H "Content-Type: application/json" \
  -d '{ "query": "typescript best practices", "max_results": 2 }'
```

Check three things in the response:

1. The status is `200`.
2. `results` has at most two entries, because `max_results` is an upper bound. Each entry has a `title` and a `url`.
3. Most entries have a `snippet`. This is the text your code now reads. It is optional in the response, so handle an entry without one.

Then add your key: change the path to `/v1/search` and send `X-API-Key`. The response gains a `usage` object. See [API keys](https://docs.keenable.ai/api-keys.md).

To compare your old provider and Keenable on your own queries before you switch, follow [Evaluate search APIs](https://docs.keenable.ai/guides/evaluate-search-apis.md). For public numbers, see [Benchmarks](https://docs.keenable.ai/benchmarks.md).


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