Browse tools

Aimed at developers running long, cited research jobs in the background, though Google hasn't published pricing or regions.

Kenning's take

What it does

Deep Research Max is an autonomous research agent in the Gemini API that spends extra compute to search, reason and refine long, cited reports. It can search the web, uploaded files and private data through MCP servers, and draw charts and infographics in its reports. Google pitches it for background jobs such as overnight due diligence reports, with a faster Deep Research agent for interactive use.

  • Built on Gemini 3.1 Pro
  • MCP support for private and paid data sources
  • Native charts and infographics
  • Review and edit the research plan before it runs
  • Works with Google Search, URL Context, Code Execution and File Search

Who it suits. Developers and companies building research workflows in fields such as finance and life sciences.

Key facts

Made by
Google DeepMind
Released
21 April 2026
How to get it
in the Gemini API for developers
Works on
API

FAQ

When was Deep Research Max released?

Google announced Deep Research and Deep Research Max on 21 April 2026.

What is the difference between Deep Research and Deep Research Max?

Deep Research is tuned for speed in interactive apps. Deep Research Max uses more compute for more complete reports and suits background jobs.

How do I use Deep Research Max?

Through the Gemini API, where developers can connect web search, files and MCP data sources.

Facts from the maker's own pages and the sources listed. Checked 2026-10-11.

Similar tools

Gemini CLI

Google's open-source AI agent that runs Gemini in the terminal for coding and other tasks

Gemini Computer Use

Gemini API tool that lets AI agents operate browsers, phones and desktops through screenshots

Gemini Deep Research Agent

Gemini API agent that plans and runs multi-step web research and returns cited reports

Gemini Enterprise Agent Platform

Google Cloud's platform for building and running AI agents, which replaced Vertex AI