Source: Gemini Deep Research agent docs
Google's guide to the Deep Research agent in the Interactions API: agent IDs, background execution, streaming, collaborative planning and tools.
Contents
- What: official API documentation
- Author / publisher: Google
- Date: read 2026-11-14 (living page)
- Original: aistudio.google.com/docs/deep-research (formerly ai.google.dev/gemini-api/docs/deep-research)
Summary
Gemini Deep Research is exposed as a managed agent, not a model: you create an interaction, it plans, searches, reads and iterates for minutes, and returns a cited report.
Key claims
- Agent IDs (as of 2026-11):
deep-research-preview-04-2026(tuned for speed and streaming to a UI) anddeep-research-max-preview-04-2026(tuned for maximum comprehensiveness). Preview status. - Only available through the Interactions API (
client.interactions.create(agent=..., input=...)), notgenerate_content; follow-ups useprevious_interaction_id. background=Trueis required; pollinteractions.get(id)untilcompletedorfailed.- Streaming:
stream=Trueplusthinking_summaries: "auto"yieldsthought,textandimagedeltas; streams can drop (600-second timeout) and resume withlast_event_id. - Default tools:
google_search,url_context,code_execution; optionalfile_searchover your document stores andmcp_server(with headers andallowed_tools). collaborative_planning: truereturns a proposed plan for the user to refine before research starts.- Optional charts (
visualization: "auto"), image and PDF inputs, and report structure steered by the prompt.