# Gemini 3.8 Flash

Google's most intelligent Flash model with significant gains over 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning. Multimodal input accepting text, images, video, audio, and documents/PDFs.

## Overview

- **Provider:** Google
- **Model ID:** `gemini-3.8-flash`
- **Type:** Chat
- **Canonical URL:** https://modelstack.cc/models/chat/gemini-3.8-flash
- **Version:** 3.8 Flash
- **Best for:** Software engineering, multi-file agentic tasks, multi-step reasoning, multimodal analysis (image/video/audio/PDF)

## Pricing

| Usage | Price |
| --- | ---: |
| Input | $1.5 / 1M tokens |
| Output | $7.5 / 1M tokens |
| Cache read | $0.15 / 1M tokens |
| Cache write (5 minutes) | $1.5 / 1M tokens |

## Specifications

- **Context window:** 1M
- **Maximum output:** 66K
- **Typical latency:** 10 ms
- **Released:** 2026-09-02

## Capabilities

- chat
- tool_use
- reasoning
- coding
- analysis

## API usage

Use this model ID in a ModelStack API request:

```json
{
  "model": "gemini-3.8-flash"
}
```

For the rendered page, visit https://modelstack.cc/models/chat/gemini-3.8-flash.