Questa sezione non è ancora tradotta. Il contenuto seguente è mostrato in inglese, come pubblicato. Leggi la versione inglese.

Google · Research

Gemini Deep Research agent (API)

Name: Gemini Deep Research agent (API)
Author: Google

Best for: Long cited research reports from an API.

See noteEntry price

NoFree tier

–MCP

NoOpen source

Checked 1 Nov 2026. A dash means not published on the sources we checked. Price source ai.google.dev (opens in a new tab)

Full sourced profile

Maker	Google
Category	Research
Skill needed	Developer
Underlying models	Gemini models ai.google.dev (opens in a new tab)
Free tier	No ai.google.dev (opens in a new tab)
Plans and tiers	–
Paid plans	–
Runs on	Cloud ai.google.dev (opens in a new tab)
Autonomy	Can run unattended ai.google.dev (opens in a new tab)
MCP support	–
A2A support	–
Open source	No ai.google.dev (opens in a new tab)
Integrations	–
Status	–
Launched	–
Best for	Long cited research reports from an API
Limitations	Cost per report varies with depth

Tools and MCP connectors that fit

Gemini Deep Research agent (API) does not state MCP support on the sources we checked, so we do not match it to MCP servers. Browse AI tools

Similar alternatives

Most shared jobs and the same category first, then the closest entry price. A similarity, not a ranking.

Perplexity (Pro and Max research)Perplexity · Research · From US$200 a month
CrewAICrewAI · Framework or SDK · See note
Gemini app agent modeGoogle · Assistant with agent mode · From £4.49 a month
Gemini managed agents (Antigravity agent)Google · Enterprise platform · See note

Compare Gemini Deep Research agent (API) with Perplexity (Pro and Max research) and CrewAI

All 42 AI agents · AI models · How we check sources

Latest news from Google

All AI news

Google 11 November 2026

Google DeepMind releases Gemini Robotics 2.5 for real-world robots

DeepMind says its new vision-language-action model, built with Gemini 4 Argon, was tested on more than 200 tasks, finishes tasks 20% to 30% faster than the previous version and packed automotive parts with a 96% success rate in proof-of-concept tests at Mercedes-Benz. It is rolling out through partners including Agile Robots, Apptronik and Boston Dynamics. The figures are DeepMind's own; more robot training and inference means more GPU demand in data centres.

Source: SiliconANGLE (opens in a new tab)

Google 30 October 2026

One robots.txt line to opt a website out of AI training

Google says it will support a shared AI training control in robots.txt, alongside Microsoft, OpenAI and Anthropic. It is based on an IETF draft. Website owners get one switch instead of one per crawler.

Source: Google Search Central Blog (opens in a new tab)

Google 28 October 2026

Google Cloud revenue more than doubles as Alphabet spends $51.4bn in a quarter

Alphabet put $51.4bn into capex in Q3, about 35% of its technical infrastructure spend going to data centres. Google Cloud revenue grew 103% to $30.7bn.

Source: Alphabet (SEC exhibit 99.1) (opens in a new tab)