> ## 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 from Linkup to Keenable

> Move a Linkup integration to Keenable: map /v1/search, depth and outputType to POST /v1/search, field by field, with before and after code.

Replace Linkup `/v1/search` calls with Keenable's `POST /v1/search`. This page maps `depth`, `outputType` and the other Linkup parameters and response fields to Keenable, lists what has no equivalent, and shows the same request on both APIs.

## Migrate with your coding agent

Paste this prompt into your coding agent. Your agent reads this page as markdown and rewrites your calls.

```text theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
Migrate this project from Linkup to Keenable. Read https://docs.keenable.ai/migrate/linkup.md for the endpoint, parameter and response maps. Replace every call with the Keenable SDK call or REST request it maps to, remove the parameters marked None, and read KEENABLE_API_KEY from the environment. Then run one request and show me the result. If a call fails, stop and show me the error.
```

Your agent finishes by running one Keenable request and showing you the result. The prompt works with Claude Code, Cursor, Codex and any other agent that can read a URL.

## What changes

| | Linkup | Keenable |
| - | - | - |
| Search request | `POST https://api.linkup.so/v1/search` with a JSON body. `q`, `depth` and `outputType` are required. | `POST https://api.keenable.ai/v1/search` with a JSON body. Only `query` is required. |
| Auth header | `Authorization: Bearer <token>` | `X-API-Key: $KEENABLE_API_KEY`, or no key on `/v1/search/public` |
| Field names | camelCase, such as `maxResults` | snake\_case, such as `max_results` |
| Output | Search results, a sourced answer or structured output, picked with `outputType`. Structured output with `includeSources` comes back as `data` and `sources`. | Search results only: a `results` list |

## Endpoint map

| Linkup | Keenable | Match | Notes |
| - | - | - | - |
| `POST /v1/search` | `POST /v1/search` | Closest | Maps `outputType: searchResults`. A sourced answer or structured output has no equivalent. |

## Parameter map

A parameter Keenable doesn't list returns `400` with `Unknown parameter(s)`, so remove Linkup parameters instead of sending them along. "Closest" means the Keenable parameter does a similar job with a different format or behavior, described in the notes.

| Linkup parameter | Keenable | Match | Notes |
| - | - | - | - |
| `q` | `query` | Exact | Quoted phrases, `site:` and `-` work as operators in Keenable too. |
| `depth` | `mode` | Closest | `flash` is closest to `realtime`, the fastest mode. `fast`, `standard` and `deep` are closest to `pro`, the default. |
| `maxResults` | `max_results` | Exact | Keenable takes `1` to `50` and defaults to `10`. |
| `includeDomains` | `site` | Closest | `site` takes one site, and a path narrows further. For several, put `site:a.com OR site:b.com` in `query`. |
| `excludeDomains` | `exclude_domains` | Exact | A list of host names. Each also covers its subdomains. |
| `fromDate` | `published_after` | Exact | Same `YYYY-MM-DD` format. Also takes a relative delta such as `7d`. |
| `toDate` | `published_before` | Exact | Same `YYYY-MM-DD` format. |
| `outputType` | None | None | Not needed. Keenable always returns a `results` list, like `searchResults`. |
| `structuredOutputSchema` | None | None | Pass the snippets to your own model with your schema. Remove `includeSources` too. |
| `includeInlineCitations` | None | None | Remove it. Cite each result's `url` from your own model's answer. |
| `includeImages` | None | None | Remove it. |

## Response map

| Linkup field | Keenable | Match | Notes |
| - | - | - | - |
| `results` | `results` | Exact | Best match first. |
| `results[].name` | `results[].title` | Exact | |
| `results[].url` | `results[].url` | Exact | |
| `results[].content` | `results[].snippet` | Closest | Markdown text from the page, capped by `snippet_max_length`. Optional, so handle a result without one. |
| `results[].favicon` | None | None | Remove code that reads it. |
| `results[].type` | None | None | Every Keenable result is a web page, so there is no `text` or `image` type. |
| `answer` | None | None | Pass the snippets to your own model. |
| `sources` | `results` | Closest | With `sourcedAnswer`, or `structured` with `includeSources`, read `results` instead. `sources[].snippet` maps to `results[].snippet`. |

## Before and after

This search asks both APIs for 5 pages published since 1 January 2025. The Keenable request runs without a key.

```bash Linkup (before) theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
curl -X POST https://api.linkup.so/v1/search \
  -H "Authorization: Bearer $LINKUP_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "q": "Microsoft fiscal year 2025 revenue",
    "depth": "fast",
    "outputType": "searchResults",
    "maxResults": 5,
    "fromDate": "2025-01-01"
  }'
```

```bash Keenable (after) 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": "Microsoft fiscal year 2025 revenue",
    "max_results": 5,
    "published_after": "2025-01-01"
  }'
```

The Keenable response has `query`, `mode` and up to 5 `results`. Each result has a `title` and a `url`, and usually a `snippet` and a `published_at`. Read `title` where you read `name`, and `snippet` where you read `content`.

## No equivalent in Keenable

These Linkup features have no Keenable counterpart. Remove them from the request, or handle them in your own code as described.

* `outputType: sourcedAnswer`: Keenable returns sources, not a generated answer. Pass the `snippet` text to your own model and cite each `url`.
* `outputType: structured`: Keenable returns no structured output, with or without `includeSources`. Pass the snippets to your own model with your JSON schema, and read sources from `results`.
* `includeImages`: Search returns web pages only, with no image results.

Mapping checked on 2026-11-19 against [docs.linkup.so/pages/documentation/endpoints/search/reference.md](https://docs.linkup.so/pages/documentation/endpoints/search/reference.md).

## Use an SDK

This program sends the same search as the Keenable tab above with the official SDK. It runs without a key and prints the title and URL of each result.

```typescript TypeScript theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
import { Keenable } from "keenable";

async function main() {
  const client = new Keenable(); // keyless: no API key needed to try it
  const results = await client.search("Microsoft fiscal year 2025 revenue", {
    maxResults: 5,
    publishedAfter: "2025-01-01",
  });
  for (const result of results.results) {
    console.log(result.title);
    console.log(result.url);
  }
}

main();
```

```python Python theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
from keenable import Keenable

client = Keenable()  # keyless: no API key needed to try it
results = client.search(
    "Microsoft fiscal year 2025 revenue",
    max_results=5,
    published_after="2025-01-01",
)
for result in results:
    print(result.title)
    print(result.url)
```

```go Go theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
package main

import (
	"context"
	"fmt"
	"log"

	"github.com/keenableai/keenable-sdk/go"
)

func main() {
	client, err := keenable.New(nil) // keyless: no API key needed to try it
	if err != nil {
		log.Fatal(err)
	}
	defer client.Close()

	results, err := client.Search(context.Background(), "Microsoft fiscal year 2025 revenue",
		&keenable.SearchOptions{
			MaxResults:     5,
			PublishedAfter: "2025-01-01",
		})
	if err != nil {
		log.Fatal(err)
	}
	for _, result := range results.Results {
		fmt.Println(result.Title)
		fmt.Println(result.URL)
	}
}
```

```rust Rust theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
use keenable::{Client, SearchOptions};

#[tokio::main]
async fn main() -> Result<(), keenable::Error> {
    let client = Client::new()?; // keyless: no API key needed to try it
    let results = client
        .search_with(
            "Microsoft fiscal year 2025 revenue",
            &SearchOptions {
                max_results: Some(5),
                published_after: Some("2025-01-01".into()),
                ..Default::default()
            },
        )
        .await?;
    for result in &results {
        println!("{}", result.title);
        println!("{}", result.url);
    }
    Ok(())
}
```

```bash curl 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": "Microsoft fiscal year 2025 revenue",
    "max_results": 5,
    "published_after": "2025-01-01"
  }'
```

You see up to 5 titles and URLs, each from a page published since 1 January 2025. Install the SDK for your language from [SDKs](https://docs.keenable.ai/sdks.md).

## Verify the migration

Check each item before you remove the old client:

1. Run the Keenable request from [Before and after](#before-and-after). The status is `200`.
2. `results` has at most as many entries as `max_results`. Each entry has a `title` and a `url`.
3. Your code reads `results[].title` where it read `name`, and `results[].snippet` where it read `content`, and handles a result that has no `snippet`.
4. Calls that used `sourcedAnswer` or `structured` now pass the snippets to your own model.
5. Your requests send no parameter from a None row. A leftover one returns `400` with `unknown_parameter`.
6. 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).

## Common questions

> [accordion] Trying Keenable without a key
>
> Send the request to `/v1/search/public` with an `X-Keenable-Title` header and no key. Without a key, the endpoint allows 1,000 requests per hour and 10 per second per IP address. See [Rate limits](https://docs.keenable.ai/rate-limits.md).

> [accordion] Choosing a mode for each depth
>
> Leave `mode` out to get `pro`, the default, for calls that used `fast`, `standard` or `deep`. Set `mode` to `realtime` for calls that used `flash`. Each mode is billed as its own SKU. See [Search](https://docs.keenable.ai/products/search.md).

> [accordion] Sourced answers
>
> Keenable returns sources and has no `answer` field. Pass each result's `snippet` to your own model and ask it to answer with citations to the `url` values.

> [accordion] Full page text
>
> Each result's `snippet` holds page text, capped by `snippet_max_length`, up to `10000` characters. For the whole page, call `GET /v1/fetch` with the result's `url`. See [Fetch](https://docs.keenable.ai/products/fetch.md).

> [accordion] Cost of each call
>
> Each search mode and each kind of fetch is billed as its own SKU, and a call made with a key returns what it cost in `usage`. See [Pricing](https://docs.keenable.ai/pricing.md) and [Balance and usage](https://docs.keenable.ai/credits.md).

## Related

* [Migrate to Keenable](https://docs.keenable.ai/migrate.md): every provider Keenable has a mapping for.
* [Migrate from Tavily](https://docs.keenable.ai/migrate/tavily.md): another search API with a generated answer, mapped to search.
* [Search API reference](https://docs.keenable.ai/api-reference/search.md): every search parameter and response field.


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