A powerful agentic researcher designed for autonomous, multi-step investigations that synthesize complex information into comprehensive, cited reports. Powered by Gemini 3.1 Pro, this model is optimized for long-running tasks and accuracy-critical analysis across hundreds of public web sources and private workspace data like Gmail and Drive.
Documentation
Visit the Deep Research page for full coverage of features and capabilities.
deep-research-pro-preview-12-2025
| Property | Description |
|---|---|
| Agent code | Interactions API deep-research-pro-preview-12-2025 |
| Supported data types | Input Text, Image, PDF, Audio, Video Output Text (Cited Reports) |
| 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-pro-preview-12-2025 |
| Latest update | December 2025 |
[*] ↩︎