Repository Public
1# Deep Research preview23<br />45A powerful agentic researcher designed for autonomous, multi-step investigations6that synthesize complex information into comprehensive, cited reports. This7model supports collaborative planning, visualization, MCP servers, and File8Search. It comes in two versions: Deep Research for speed and efficiency, and9Deep Research Max for maximum comprehensiveness.1011## Documentation1213Visit the [Deep Research](https://ai.google.dev/gemini-api/docs/deep-research) page for full coverage14of features and capabilities.1516## deep-research-preview-04-20261718| Property | Description |19|---|---|20| Agent code | **Interactions API** `deep-research-preview-04-2026` |21| Supported data types | **Input** Text, Image, PDF, Audio, Video **Output** Text (Cited Reports), Images |22| Token limits^[\[\*\]](https://ai.google.dev/gemini-api/docs/tokens)^ | **Input context window** 1,048,576 **Output token limit** 65,536 |23| Versions | Read the [model version patterns](https://ai.google.dev/gemini-api/docs/models/gemini#model-versions) for more details. - Preview: `deep-research-preview-04-2026` - Max: `deep-research-max-preview-04-2026` |24| Latest update | April 2026 |