# Gemini 3 Flash Preview

Best multimodal understanding model. Frontier performance at lower cost. Supports computer use.

## Overview

- **Provider:** Google
- **Model ID:** `gemini-3-flash`
- **Type:** Chat
- **Canonical URL:** https://modelstack.cc/models/chat/gemini-3-flash
- **Version:** 3 Flash
- **Best for:** Multimodal understanding, agentic workflows, computer use, vibe coding

## Pricing

| Usage | Price |
| --- | ---: |
| Input | $0.5 / 1M tokens |
| Output | $3 / 1M tokens |
| Cache read | $0.05 / 1M tokens |
| Cache write (5 minutes) | $0.083333 / 1M tokens |

## Specifications

- **Context window:** 1.05M
- **Maximum output:** 66K
- **Released:** 2025-12

## Capabilities

- chat
- tool_use
- coding

## API usage

Use this model ID in a ModelStack API request:

```json
{
  "model": "gemini-3-flash"
}
```

For the rendered page, visit https://modelstack.cc/models/chat/gemini-3-flash.