aiaimodel.cards

Gemini 2.5 Flash-Lite

Language modelPrevious generationCard summarized

Our most cost-efficient multimodal model, offering the fastest performance for high-frequency, lightweight tasks

Active; access limited to existing users● Re-checked 12 Oct 2026 · 21 facts · 0 correctionsSource: Gemini 2.5 Flash-Lite Model Card (9 pp)

Use it via API

$55.80 /month
$1.12 per 1K requests
RAG over docs: 12K in · 600 out · 50K requests/mo · 30% cached · change
Code exampleCompare

Where to call it

  • Gemini APIgemini-2.5-flash-lite

Supports

  • Structured outputs
  • Tool calling
  • Web search
  • Batch API
  • Image input
  • PDF input
  • Prompt caching
Full feature support

Good for

  • High-volume, low-cost, low-latency tasks
  • Translation and classification (p.2)

Watch out for

Replaced by

Gemini 3.5 Flash-Lite$0.30 / $2.50

This model: $0.10 / $0.40 per 1M tokens

Compare side by side

Overview

Google · 08Flash-Lite, front

2.5 Flash-Lite

Our most cost-efficient multimodal model, offering the fastest performance for high-frequency, lightweight tasks

Cost
$0.10 in
Context
1M
Input / output
$0.10 / $0.40
Max output
64K
Knows up to
January 2025
Released
22 Jul 2025

A hybrid reasoning model where developers can turn thinking on or off. It is cost-efficient and fast, optimized for high-volume, latency-sensitive tasks such as translation and classification, and improves on 2.0 Flash-Lite in coding, math, science and reasoning. p.2

gemini-2.5-flash-lite
Input / output per 1M
$0.10 / $0.40
Context window
1M
Max output
64K
Knows up to
January 2025
Reasoning
Off by default, thinking_level low / medium / high
Weights
Closed

About this card. A model card is the maker's own account of a model: what it's for, how it was trained and tested, and where it falls short. This page condenses Google DeepMind's Gemini 2.5 Flash-Lite Model Card. Every claim carries its source page.