> 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 Deep Research

> Research model for multi-step retrieval, synthesis, and reasoning, autonomously searching, reading, and evaluating sources across complex topics.

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

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

`POST /v1/chat/completions`

Research model for multi-step retrieval, synthesis, and reasoning, autonomously searching, reading, and evaluating sources across complex topics.

## At a glance

| Field               | Value                                                                                                                                                     |
| ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Model id            | `perplexity-deep-research`                                                                                                                                |
| Model release date  | -                                                                                                                                                         |
| Input modalities    | Text, Image, Document                                                                                                                                     |
| Output modalities   | Text                                                                                                                                                      |
| Context window      | 128K                                                                                                                                                      |
| Weight precision    | -                                                                                                                                                         |
| 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-deep-research:generateContent` |

## Pricing

| Charge           | Spec                    | Rate    |
| ---------------- | ----------------------- | ------- |
| Input            | per 1M prompt tokens    | \$4.80  |
| Output           | per 1M generated tokens | \$19.00 |
| Citation Tokens  | per 1M tokens           | \$4.80  |
| Reasoning Tokens | per 1M tokens           | \$7.20  |
| Search Queries   | per query               | \$0.012 |

## Example request

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

## Parameters

| Parameter                    | Type    | Required | Default    | Description                                                                                                                                                                                                                                      |
| ---------------------------- | ------- | -------- | ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `max_tokens`                 | number  | no       | -          | Maximum tokens in the response, at least 16. When omitted, the model's own default applies. · Range: 16 – 65536                                                                                                                                  |
| `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`                                                                                        |
| `search_domain_filter`       | string  | no       | -          | Comma-separated domains. Prefix with '-' to exclude. Max 20.                                                                                                                                                                                     |
| `max_results`                | number  | no       | `15`       | Most results each web search returns. More results give more sources to draw on. · Range: 1 – 50                                                                                                                                                 |
| `search_after_date_filter`   | string  | no       | -          | Only include sources published after this date. Use MM/DD/YYYY or YYYY-MM-DD.                                                                                                                                                                    |
| `search_before_date_filter`  | string  | no       | -          | Only include sources published before this date. Use MM/DD/YYYY or YYYY-MM-DD.                                                                                                                                                                   |
| `search_recency_filter`      | enum    | no       | `"none"`   | Relative time filter. Cannot be combined with specific dates. · Allowed: `none`, `hour`, `day`, `week`, `month`, `year`                                                                                                                          |
| `last_updated_after_filter`  | string  | no       | -          | Only include sources last updated after this date. Use MM/DD/YYYY or YYYY-MM-DD.                                                                                                                                                                 |
| `last_updated_before_filter` | string  | no       | -          | Only include sources last updated 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 [\[N\]](url) rewriting + References block + \<think> extraction to reasoning_content). Raw mode keeps the \<think>...\</think> tags inside content so callers can parse reasoning themselves. |

## Notes

Long-running multi-step retrieval and reasoning. Pricing splits Input / Output / Citation / Reasoning tokens plus per-query search charge.

---

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