# Gemini 2.5 Flash Lite

Ultra-low latency and cost efficiency model. 90% cheaper cache reads. Optimized for high-volume production workloads.

## Overview

- **Provider:** Google
- **Model ID:** `gemini-2.5-flash-lite`
- **Type:** Chat
- **Canonical URL:** https://modelstack.cc/models/chat/gemini-2.5-flash-lite
- **Version:** 2.5 Flash Lite
- **Knowledge cutoff:** 2025-01
- **Best for:** High-volume tasks, classification, translation, intelligent routing, cost-sensitive workloads

## Pricing

| Usage | Price |
| --- | ---: |
| Input | $0.1 / 1M tokens |
| Output | $0.4 / 1M tokens |
| Cache read | $0.01 / 1M tokens |
| Cache write (5 minutes) | $0.083333 / 1M tokens |

## Specifications

- **Context window:** 1.05M
- **Maximum output:** 66K
- **Typical latency:** 6 ms
- **Released:** 2026-05

## Capabilities

- chat
- tool_use
- coding

## API usage

Use this model ID in a ModelStack API request:

```json
{
  "model": "gemini-2.5-flash-lite"
}
```

For the rendered page, visit https://modelstack.cc/models/chat/gemini-2.5-flash-lite.
