Gemini 3.1 Pro
Definition
Gemini 3.1 Pro is a Google model version for complex tasks with multimodal inputs and text output.
The documented variant Gemini 3.1 Pro Preview processes text, images, video, audio, and PDF and outputs text. Google mentions, among other things, structured output, function calls, and a reasoning mode. The identifier is gemini-3.1-pro-preview.
Simply explained
Like a workbook into which you put text, images, and sound and get a written elaboration back. The workbook does not guarantee error-free interpretation of its content.
Why it matters in practice
In document processes, the actually supported input type counts. The model page lists these separately from output modalities and tool functions.
Example from business
Possible example: A team tests the summarization of released PDF documents and checks the answers against the original.
Limits and pitfalls
- The documented variant is marked as Preview. Image and audio inputs do not mean image or audio output; the model page indicates both output types as not supported.
Origin & history
The model page names February 2026 as the latest model update of the documented variant. This date is not equated with the webpage's modification date.
Use in mid-sized companies
- Possible applications are the evaluation of mixed documents, preparatory code analyses, and tests of structured text outputs.
Frequently asked questions
Can this variant generate images?
The cited model page denies image generation.
Is the Customtools endpoint usable identically?
Google describes it as a separate variant for certain tool workflows and points out possible quality fluctuations.
Sources
- Gemini 3.1 Pro preview · Google (2026): Gemini 3.1 Pro preview
Editorially reviewed on: