Deep Research Max preview
Maximum comprehensiveness for automated context gathering and synthesis. Deep Research Max is optimized for long-running, accuracy-critical investigations that synthesize complex information from hundreds of public web sources and private workspace data into comprehensive, cited reports. It supports collaborative planning, visualization, MCP servers, and File Search.
Documentation
Visit the Deep Research page for full coverage of features and capabilities.
deep-research-max-preview-04-2026
| Property | Description |
|---|---|
| Agent code | Interactions API deep-research-max-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-max-preview-04-2026 |
| Latest update | April 2026 |
[*] ↩︎