# Gemini 3.5 Flash

~4× faster than frontier models. Optimized for agent workflows, multi-file coding, document analysis. Multimodal input (text, images, audio, video, PDFs).

## Overview

- **Provider:** Google
- **Model ID:** `gemini-3.5-flash`
- **Type:** Chat
- **Canonical URL:** https://modelstack.cc/models/chat/gemini-3.5-flash
- **Version:** 3.5 Flash
- **Knowledge cutoff:** 2025-01
- **Best for:** Agent workflows, multi-file coding, document analysis, multimodal tasks

## Pricing

| Usage | Price |
| --- | ---: |
| Input | $1.5 / 1M tokens |
| Output | $9 / 1M tokens |
| Cache read | $0.15 / 1M tokens |
| Cache write (5 minutes) | $1 / 1M tokens |

## Specifications

- **Context window:** 1M
- **Maximum output:** 66K
- **Typical latency:** 12 ms
- **Released:** 2026-05-19

## Capabilities

- chat
- tool_use
- reasoning
- coding
- analysis

## API usage

Use this model ID in a ModelStack API request:

```json
{
  "model": "gemini-3.5-flash"
}
```

For the rendered page, visit https://modelstack.cc/models/chat/gemini-3.5-flash.