The Gemini Deep Research Agent is a managed AI agent designed to plan, execute, and synthesize complex, multi-step research workflows. Powered by Gemini, the agent navigates diverse information landscapes including the public web and private enterprise data to generate comprehensive, cited reports that accelerate informed decision-making.
For more information on how to get started using Deep Research, see Use the Gemini Deep Research Agent .
Agent ID
deep-research-preview-04-2026
Supported APIs
- Interactions API
Supported inputs & outputs
- Inputs:
Text , PDF - Outputs:
Text , Images
Token limits
- Maximum input tokens: 1,048,576
- Maximum output tokens: 65,536
Capabilities
- Supported
- Not supported
- Supported
- Not supported
Technical specifications
Documents
- Maximum number of files per prompt: 3,000
- Maximum number of pages per file: 3,000
- Maximum file size per file for the API or Cloud Storage imports: 50 MB (application/pdf) or 7 MB (text/plain)
- Maximum file size per file for direct uploads through the console: 7 MB
- Default resolution tokens: 560
- OCR for scanned PDFs: Not used by default
- Supported MIME types:
application/pdf,text/plain
Supported regions
Agent availability
- Global
- global
Knowledge cutoff date
January 2025
Quota name
Stateful Gen AI Interaction Creation requests per minute
Billing label
is_deep_research
Supported languages
Pricing
