GoogleGemini 3
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview is a preview API for multimodal reasoning.
Preview
What the release provides
It accepts text, image, video, audio and PDF input and returns text. The model has a million-token input allowance and supports tool-based workflows; its preview label remains part of the API identity.Gemini 3.1 Pro Preview official API documentation
How to use it well
Practical guidance. Keep a record of the exact preview model and request settings used for an evaluation. Review long-document answers against cited passages. Before using a replacement, compare how it selects and sequences tools rather than comparing only final prose.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Preview |
| Access | API |
| Model identifiers | gemini-3.1-pro-preview |
| Context window | 1,048,576 tokens API input limit; reserve output capacity where the service shares one window. Gemini 3.1 Pro Preview official API documentation |
| Maximum output | 65,536 tokens Published API output limit; request settings can be lower. Gemini 3.1 Pro Preview official API documentation |