> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.empiriolabs.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server.

# Linkup Deep Search

> Iterative AI search that keeps querying when initial results are insufficient, returning more comprehensive answers than Standard mode.

![Linkup Deep Search](https://media.empiriolabs.ai/model-logos/linkup-deep-search.png)

[Linkup](/providers/linkup) · Research & Search

`POST /v1/search`

Iterative AI search that keeps querying when initial results are insufficient, returning more comprehensive answers than Standard mode.

## At a glance

| Field               | Value                                                                                                                                               |
| ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------- |
| Model id            | `linkup-deep-search`                                                                                                                                |
| Model release date  | -                                                                                                                                                   |
| Input modalities    | Text                                                                                                                                                |
| Output modalities   | Text                                                                                                                                                |
| Context window      | 100K                                                                                                                                                |
| Weight precision    | -                                                                                                                                                   |
| Features            | web_search, deep_research                                                                                                                           |
| Native inference    | No                                                                                                                                                  |
| New                 | No                                                                                                                                                  |
| Supported endpoints | `POST /v1/search`, `POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages`, `POST /v1beta/models/linkup-deep-search:generateContent` |

## Pricing

| Charge      | Spec  | Rate   |
| ----------- | ----- | ------ |
| Per Message | fixed | \$0.13 |

## Example request

```bash
curl https://api.empiriolabs.ai/v1/search \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "linkup-deep-search", "query": "latest LLM benchmarks 2026"}'
```

## Parameters

| Parameter                 | Type    | Required | Default           | Description                                                                                                                                                                          |
| ------------------------- | ------- | -------- | ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `query`                   | string  | yes      | -                 | The natural-language query to search/research/answer.                                                                                                                                |
| `output_type`             | enum    | no       | `"sourcedAnswer"` | sourcedAnswer returns a synthesized answer with citations; searchResults returns raw hits and is returned by POST /v1/search only. · Allowed: `sourcedAnswer`, `searchResults`       |
| `domain_filter_mode`      | enum    | no       | `"None"`          | None applies whichever domain lists you send. Include returns results only from include_domains. Exclude drops results from exclude_domains. · Allowed: `None`, `Include`, `Exclude` |
| `include_domains`         | string  | no       | -                 | Comma-separated domains or URLs to include                                                                                                                                           |
| `exclude_domains`         | string  | no       | -                 | Comma-separated domains or URLs to exclude                                                                                                                                           |
| `prioritize_domains`      | string  | no       | -                 | Comma-separated domains to prefer via query guidance                                                                                                                                 |
| `from_date`               | string  | no       | -                 | Only include sources published on or after this date. Format: YYYY-MM-DD.                                                                                                            |
| `to_date`                 | string  | no       | -                 | Only include sources published on or before this date. Format: YYYY-MM-DD.                                                                                                           |
| `include_images`          | boolean | no       | false             | Include relevant image URLs in the results.                                                                                                                                          |
| `image_count`             | number  | no       | `6`               | Maximum number of images returned. · Range: 1 – 45                                                                                                                                   |
| `enable_inline_citations` | boolean | no       | true              | Embed \[N] citations inline in the synthesized answer.                                                                                                                               |
| `include_sources`         | boolean | no       | true              | Return the list of source URLs alongside the answer.                                                                                                                                 |
| `max_results`             | number  | no       | -                 | Maximum number of results returned. · Range: 1 – 100                                                                                                                                 |

## Notes

Iterative search, retries when initial results are insufficient.

---

*Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/linkup-deep-search`.