> 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.

# Perplexity Advanced Deep Research

> Institutional-grade research agent that runs many rounds of web search and page reading, with maximum depth and extensive source coverage.

![Perplexity Advanced Deep Research](https://media.empiriolabs.ai/model-logos/perplexity-adv-deep-research.png)

[Perplexity](/providers/perplexity) · Research & Search

`POST /v1/chat/completions`

Institutional-grade research agent that runs many rounds of web search and page reading, with maximum depth and extensive source coverage.

## At a glance

| Field               | Value                                                                                                                                                              |
| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Model id            | `perplexity-advanced-deep-research`                                                                                                                                |
| Model release date  | -                                                                                                                                                                  |
| Input modalities    | Text, Image, Document                                                                                                                                              |
| Output modalities   | Text                                                                                                                                                               |
| Context window      | -                                                                                                                                                                  |
| Weight precision    | -                                                                                                                                                                  |
| Max output tokens   | 16,000                                                                                                                                                             |
| Features            | web_search, reasoning, deep_research                                                                                                                               |
| Native inference    | No                                                                                                                                                                 |
| New                 | No                                                                                                                                                                 |
| Supported endpoints | `POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages`, `POST /v1/search`, `POST /v1beta/models/perplexity-advanced-deep-research:generateContent` |

## Pricing

| Charge          | Spec                    | Rate     |
| --------------- | ----------------------- | -------- |
| Input           | per 1M prompt tokens    | \$12.00  |
| Output          | per 1M generated tokens | \$60.00  |
| Web Search Call | per call                | \$0.012  |
| URL Fetch Call  | per call                | \$0.0012 |

## Example request

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

## Parameters

| Parameter               | Type    | Required | Default    | Description                                                                                                                                                                                                                                                                                         |
| ----------------------- | ------- | -------- | ---------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `reasoning_effort`      | enum    | no       | `"medium"` | How much the model reasons while it researches. high is the most thorough, takes the longest and uses the most tokens. · Allowed: `low`, `medium`, `high`                                                                                                                                           |
| `max_output_tokens`     | number  | no       | `10000`    | Maximum tokens in the final answer (does not count research steps). Range 10000-16000. · Range: 10000 – 16000                                                                                                                                                                                       |
| `max_tokens_per_page`   | number  | no       | `4096`     | Max tokens extracted per search result page, from 1 to 16384. Higher = more content per source but slower. · Range: 1 – 16384                                                                                                                                                                       |
| `max_results`           | number  | no       | `15`       | Most results each web search returns. More results give more sources to draw on. · Range: 1 – 50                                                                                                                                                                                                    |
| `search_domain_filter`  | string  | no       | -          | Comma-separated domains. Prefix with '-' to exclude. Max 20.                                                                                                                                                                                                                                        |
| `search_recency_filter` | enum    | no       | `"none"`   | Relative time filter. Cannot be combined with specific dates. · Allowed: `none`, `hour`, `day`, `week`, `month`, `year`                                                                                                                                                                             |
| `search_after_date`     | string  | no       | -          | Only include sources published after this date. Use MM/DD/YYYY or YYYY-MM-DD.                                                                                                                                                                                                                       |
| `search_before_date`    | string  | no       | -          | Only include sources published before this date. Use MM/DD/YYYY or YYYY-MM-DD.                                                                                                                                                                                                                      |
| `country`               | string  | no       | -          | Two-letter ISO 3166-1 code (e.g. US, GB) for biasing results to a country.                                                                                                                                                                                                                          |
| `region`                | string  | no       | -          | State or province name for location bias.                                                                                                                                                                                                                                                           |
| `city`                  | string  | no       | -          | City name for location bias.                                                                                                                                                                                                                                                                        |
| `latitude`              | number  | no       | -          | Latitude for location bias, in decimal degrees.                                                                                                                                                                                                                                                     |
| `longitude`             | number  | no       | -          | Longitude for location bias, in decimal degrees.                                                                                                                                                                                                                                                    |
| `disable_formatting`    | boolean | no       | false      | Skip the EmpirioLabs Markdown formatting (citation hyperlinks + References block + reasoning_content render). The plain answer text and the structured reasoning_steps array (with search queries, results, and fetched URLs) are still returned. Applies to /v1/chat/completions and /v1/messages. |

---

*Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/perplexity-advanced-deep-research`.