Gemini 3 Pro Preview

gemini-3-pro-preview

Google's best model for multimodal understanding and the most powerful agentic model yet. Delivers richer visuals and deeper interactivity with state-of-the-art reasoning capabilities across text, images, video, audio, and PDFs.

Deprecated Model

This model has been deprecated and is no longer recommended for new projects.Retiring on March 8, 2026

Use this model with Aisle

Chat

Have natural conversations with the model in a familiar interface

Prompts

Automate tasks, share with your team, and deploy to chat

Playgrounds

Test prompt variants, model settings, and compare models side by side

Workflows

Chain prompts together for complex automation and outcomes

Context Window

1049K

tokens

Temperature

0 – 2

default: 1

Extended Thinking

Supported

Web Search

Available

MCP Support

Available

Structured Output

Available

Supported File Formats

Images

WEBP(5 MB)PNG(5 MB)JPEG(5 MB)GIF(5 MB)

Documents

pdftextdocxlsrtfdocxxlsxpptxpptodtodpods