# Deep Research Agent (Brave + Gemini 3.1/GPT-5.1/Opus4.6) (`visita/deep-research-agent`) Actor
π¦ Autonomous research assistant. Uses Brave Search + AI (Gemini 3.1/GPT-5.1/Opus4.6) to search, scrape, and synthesize the web into professional, fully cited reports. π Features instant HTML/Markdown export and massive context windows. Perfect for market intelligence, academic research, & briefs.
- **URL**: https://apify.com/visita/deep-research-agent.md
- **Developed by:** [Visita Intelligence](https://apify.com/visita) (community)
- **Categories:** AI, Agents, Developer tools
- **Stats:** 14 total users, 2 monthly users, 0.0% runs succeeded, 2 bookmarks
- **User rating**: No ratings yet
## Pricing
from $50.00 / 1,000 standard modes
This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.
Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event
## What's an Apify Actor?
Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".
## How to integrate an Actor?
If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.
In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md):
```bash
npm install apify-client
```
In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md):
```bash
pip install apify-client
```
In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md):
````bash
# MacOS / Linux
curl -fsSL https://apify.com/install-cli.sh | bash
# Windows
irm https://apify.com/install-cli.ps1 | iex
```bash
In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md).
If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md).
For usage examples, see the [API](#api) section below.
For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).
# README
## π¦ Deep Research Agent
**The autonomous AI research assistant that browses, reads, analyzes, and synthesizes the web for you.**
---
### π€― The Problem: Search is Noisy
When you Google a complex topic like *"The impact of quantum computing on cryptography,"* you get 10 blue links.
* You have to click every link.
* You have to dodge ads and popups.
* You have to read 5,000 words just to find one specific fact.
* **It takes hours.**
### π‘ The Solution: Deep Research Agent
This Actor acts like a **human research assistant**. It does the heavy lifting for you automatically, saving you massive amounts of time:
1. **Searches** the web using the ad-free Brave Search API.
2. **Visits** the top websites and reads the full content (scraping text).
3. **Synthesizes** the massive amount of information using **Premium LLMs** (GPT-5.1, Claude 4.6 Opus, Gemini 3.1 Pro).
4. **Writes** a professional, fully cited report delivered in Multiple Formats.
> **β¨ Key Feature: Massive Context Window**
> Because we utilize premium massive-context models like Gemini 3.1 Pro, this actor can read dozens of long articles, PDFs, and technical documentation in a single pass without "forgetting" details.
---
### π Features
| Feature | Description |
| :--- | :--- |
| **π¦ Brave Search** | Uses the privacy-focused Brave API to find unbiased results without SEO spam. |
| **π§ Premium Multi-LLM Support** | Choose between the absolute best models on the market: **OpenAI** (GPT-5.1), **Anthropic** (Claude 4.6 Opus) or **Google** (Gemini 3.1 Pro). |
| **β‘ Flexible Research Modes** | Choose **Standard Mode** (Analyzes top 5 sources quickly) or **Deep Mode** (Analyzes up to 15 sources for comprehensive answers). |
| **π Multiple Output Formats** | Out-of-the-box generation of shareable **HTML pages, PDF documents, DOCX files**, and raw **Markdown**. |
| **π 100% Cited & Hallucination-free** | Every claim in the report is strictly grounded and linked directly to its source URL. |
| **π Zero Setup** | No Bring-Your-Own-Key (BYOK) needed! API keys for Search and Premium LLMs are handled natively by us. |
---
### π― Use Cases
#### π¬ Academic & Technical Research
* "What are the latest breakthroughs in Solid State Batteries in 2025?"
* "Summarize the current geopolitical tensions in the South China Sea."
#### π Market Intelligence
* "Analyze the pricing strategy of top 5 CRM competitors in South Africa."
* "What are the emerging trends in AI-driven agriculture?"
#### βοΈ Content Creation
* "Write a detailed outline for a blog post about 'How to use Python for SEO'."
* "Find and summarize 5 recent news stories about SpaceX."
---
### π° Pricing (Pay Per Event)
This Actor uses a highly predictable **Pay-Per-Event (PPE)** pricing model. You do not pay for compute unit hours or external API usageβeverything is bundled into a simple flat fee per report generated!
* **β‘ Standard Mode:** $0.05 per Report (Searches and analyzes the top 5 sources)
* **π΅οΈ Deep Mode:** $0.10 per Report (Searches and deeply analyzes up to 15 sources)
*Note: You do not need to configure any API keys or secrets yourself. The pricing above covers the full cost of Brave Search and the Premium LLMs.*
---
### π¦ Output Example
The Actor produces a Dataset containing the raw data, but the magic happens in the **Key-Value Store**.
You will receive direct links to download your formatted **PDF, DOCX**, and a **Hosted HTML Report** that looks like this:
`html
The State of Quantum Computing
Quantum computing has moved beyond theoretical physics into early commercialization...
- IBM Condor Processor: Now stabilizing over 1000 qubits... [1]
- Error Correction: New breakthroughs by Google DeepMind... [2]
``
**JSON Dataset Export:**
`json
{
"query": "State of Quantum Computing",
"model": "openai/gpt-5.1",
"report_html_url": "https://api.apify.com/v2/key-value-stores/.../OUTPUT_REPORT.html",
"report_pdf_url": "https://api.apify.com/v2/key-value-stores/.../OUTPUT_REPORT.pdf",
"report_docx_url": "https://api.apify.com/v2/key-value-stores/.../OUTPUT_REPORT.docx",
"report_markdown": "# Report Title...",
"sources": [
{
"title": "Quantum Computing News",
"url": "https://...",
"domain": "techcrunch.com"
}
]
}
`
-----
### β FAQ
**Q: Can I trust the citations?**
A: Yes. The AI is strictly instructed to only use information from the scraped search results. It lists every source used at the bottom of the report.
**Q: Does it work for non-English queries?**
A: Yes\! You can ask questions in Spanish, French, German, etc. The AI will research and write the report in your target language.
-----
### π Support
If you have feature requests or run into issues, please use the **Issues** tab on Apify. We actively maintain this agent to ensure compatibility with the latest AI models.
# Actor input Schema
## `query` (type: `string`):
The main question or subject you want to investigate.
## `mode` (type: `string`):
Select the depth of research. Standard explores 5 sources. Deep explores up to 15 sources for a comprehensive report.
## `customInstructions` (type: `string`):
Define the AI's tone.
## `country` (type: `string`):
Bias the search results to a specific location.
## `model` (type: `string`):
Select the AI model for synthesis.
## Actor input object example
```json
{
"query": "State of Quantum Computing in 2025",
"mode": "standard",
"customInstructions": "Be professional, objective, and heavily cited.",
"country": "US",
"model": "openai/gpt-5.1"
}
````
# Actor output Schema
## `report_html` (type: `string`):
A formatted, shareable view of your research.
## `report_pdf` (type: `string`):
Download the generated PDF format.
## `report_docx` (type: `string`):
Download the generated DOCX format.
## `dataset_overview` (type: `string`):
View the report summary and download options.
## `sources_view` (type: `string`):
See exactly which websites were used for this research.
## `full_json` (type: `string`):
The complete dataset for developers.
# API
You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.
## JavaScript example
```javascript
import { ApifyClient } from 'apify-client';
// Initialize the ApifyClient with your Apify API token
// Replace the '' with your token
const client = new ApifyClient({
token: '',
});
// Prepare Actor input
const input = {
"query": "State of Quantum Computing in 2025"
};
// Run the Actor and wait for it to finish
const run = await client.actor("visita/deep-research-agent").call(input);
// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`πΎ Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
console.dir(item);
});
// π Want to learn more π? Go to β https://docs.apify.com/api/client/js/docs
```
## Python example
```python
from apify_client import ApifyClient
# Initialize the ApifyClient with your Apify API token
# Replace '' with your token.
client = ApifyClient("")
# Prepare the Actor input
run_input = { "query": "State of Quantum Computing in 2025" }
# Run the Actor and wait for it to finish
run = client.actor("visita/deep-research-agent").call(run_input=run_input)
# Fetch and print Actor results from the run's dataset (if there are any)
print("πΎ Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
print(item)
# π Want to learn more π? Go to β https://docs.apify.com/api/client/python/docs/quick-start
```
## CLI example
```bash
echo '{
"query": "State of Quantum Computing in 2025"
}' |
apify call visita/deep-research-agent --silent --output-dataset
```
## MCP server setup
```json
{
"mcpServers": {
"apify": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.apify.com/?tools=visita/deep-research-agent",
"--header",
"Authorization: Bearer "
]
}
}
}
```
## OpenAPI specification
```json
{
"openapi": "3.0.1",
"info": {
"title": "Deep Research Agent (Brave + Gemini 3.1/GPT-5.1/Opus4.6)",
"description": "π¦ Autonomous research assistant. Uses Brave Search + AI (Gemini 3.1/GPT-5.1/Opus4.6) to search, scrape, and synthesize the web into professional, fully cited reports. π Features instant HTML/Markdown export and massive context windows. Perfect for market intelligence, academic research, & briefs.",
"version": "0.0",
"x-build-id": "Nlwi8uaZGdnPMPx6Z"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/visita~deep-research-agent/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-visita-deep-research-agent",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/visita~deep-research-agent/runs": {
"post": {
"operationId": "runs-sync-visita-deep-research-agent",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/visita~deep-research-agent/run-sync": {
"post": {
"operationId": "run-sync-visita-deep-research-agent",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
}
},
"components": {
"schemas": {
"inputSchema": {
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"title": "π¬ Research Topic",
"type": "string",
"description": "The main question or subject you want to investigate.",
"default": "State of Quantum Computing in 2025"
},
"mode": {
"title": "β‘ Research Mode",
"enum": [
"standard",
"deep"
],
"type": "string",
"description": "Select the depth of research. Standard explores 5 sources. Deep explores up to 15 sources for a comprehensive report.",
"default": "standard"
},
"customInstructions": {
"title": "π Researcher Persona",
"type": "string",
"description": "Define the AI's tone.",
"default": "Be professional, objective, and heavily cited."
},
"country": {
"title": "π Search Region",
"enum": [
"US",
"GB",
"ZA",
"CA",
"AU",
"IN",
"DE",
"FR"
],
"type": "string",
"description": "Bias the search results to a specific location.",
"default": "US"
},
"model": {
"title": "π§ AI Model",
"enum": [
"openai/gpt-5.1",
"anthropic/claude-4.6-opus",
"google/gemini-3.1-pro"
],
"type": "string",
"description": "Select the AI model for synthesis.",
"default": "openai/gpt-5.1"
}
}
},
"runsResponseSchema": {
"type": "object",
"properties": {
"data": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"actId": {
"type": "string"
},
"userId": {
"type": "string"
},
"startedAt": {
"type": "string",
"format": "date-time",
"example": "2025-01-08T00:00:00.000Z"
},
"finishedAt": {
"type": "string",
"format": "date-time",
"example": "2025-01-08T00:00:00.000Z"
},
"status": {
"type": "string",
"example": "READY"
},
"meta": {
"type": "object",
"properties": {
"origin": {
"type": "string",
"example": "API"
},
"userAgent": {
"type": "string"
}
}
},
"stats": {
"type": "object",
"properties": {
"inputBodyLen": {
"type": "integer",
"example": 2000
},
"rebootCount": {
"type": "integer",
"example": 0
},
"restartCount": {
"type": "integer",
"example": 0
},
"resurrectCount": {
"type": "integer",
"example": 0
},
"computeUnits": {
"type": "integer",
"example": 0
}
}
},
"options": {
"type": "object",
"properties": {
"build": {
"type": "string",
"example": "latest"
},
"timeoutSecs": {
"type": "integer",
"example": 300
},
"memoryMbytes": {
"type": "integer",
"example": 1024
},
"diskMbytes": {
"type": "integer",
"example": 2048
}
}
},
"buildId": {
"type": "string"
},
"defaultKeyValueStoreId": {
"type": "string"
},
"defaultDatasetId": {
"type": "string"
},
"defaultRequestQueueId": {
"type": "string"
},
"buildNumber": {
"type": "string",
"example": "1.0.0"
},
"containerUrl": {
"type": "string"
},
"usage": {
"type": "object",
"properties": {
"ACTOR_COMPUTE_UNITS": {
"type": "integer",
"example": 0
},
"DATASET_READS": {
"type": "integer",
"example": 0
},
"DATASET_WRITES": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_READS": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_WRITES": {
"type": "integer",
"example": 1
},
"KEY_VALUE_STORE_LISTS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_READS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_WRITES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_INTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_EXTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_SERPS": {
"type": "integer",
"example": 0
}
}
},
"usageTotalUsd": {
"type": "number",
"example": 0.00005
},
"usageUsd": {
"type": "object",
"properties": {
"ACTOR_COMPUTE_UNITS": {
"type": "integer",
"example": 0
},
"DATASET_READS": {
"type": "integer",
"example": 0
},
"DATASET_WRITES": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_READS": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_WRITES": {
"type": "number",
"example": 0.00005
},
"KEY_VALUE_STORE_LISTS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_READS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_WRITES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_INTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_EXTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_SERPS": {
"type": "integer",
"example": 0
}
}
}
}
}
}
}
}
}
}
```