# Gemini 3.1 Pro Preview

Most capable Gemini model. Optimized for software engineering and agentic workflows.

## Overview

- **Provider:** Google
- **Model ID:** `gemini-3.1-pro`
- **Type:** Chat
- **Canonical URL:** https://modelstack.cc/models/chat/gemini-3.1-pro
- **Version:** 3.1 Pro
- **Best for:** Complex problem-solving, agentic coding, software engineering, deep reasoning

## Pricing

| Usage | Price |
| --- | ---: |
| Input | $2 / 1M tokens |
| Output | $12 / 1M tokens |
| Cache read | $0.2 / 1M tokens |
| Cache write (5 minutes) | $0.375 / 1M tokens |

## Specifications

- **Context window:** 1.05M
- **Maximum output:** 66K
- **Typical latency:** 22 ms
- **Released:** 2026-02

## Capabilities

- chat
- tool_use
- coding

## API usage

Use this model ID in a ModelStack API request:

```json
{
  "model": "gemini-3.1-pro"
}
```

For the rendered page, visit https://modelstack.cc/models/chat/gemini-3.1-pro.