Deep Research preview
A powerful agentic researcher designed for autonomous, multi-step investigations that synthesize complex information into comprehensive, cited reports. This model supports collaborative planning, visualization, MCP servers, and File Search. It comes in two versions: Deep Research for speed and efficiency, and Deep Research Max for maximum comprehensiveness.
Documentation
Visit the Deep Research page for full coverage of features and capabilities.
deep-research-preview-04-2026
| Property | Description |
|---|---|
| Agent code | Interactions API deep-research-preview-04-2026 |
| Supported data types | Input Text, Image, PDF, Audio, Video Output Text (Cited Reports), Images |
| Token limits[1](https://ai.google.dev/gemini-api/docs/tokens)^ | Input context window 1,048,576 Output token limit 65,536 |
| Versions | Read the model version patterns for more details. - Preview: deep-research-preview-04-2026 - Max: deep-research-max-preview-04-2026 |
| Latest update | April 2026 |
[*] ↩︎