Gemini 2.5 Flash

Language modelPrevious generationCard summarized

Our best model in terms of price-performance, offering well-rounded capabilities

Active; access limited to existing users● Re-checked 12 Oct 2026 · 21 facts · 0 correctionsSource: Gemini 2.5 Flash Model Card (11 pp)

Use it via API

$206 /month

$4.13 per 1K requests

RAG over docs: 12K in · 600 out · 50K requests/mo · 30% cached · change

Code example Compare

Where to call it

Gemini APIgemini-2.5-flash

Supports

Structured outputs
Tool calling
Web search
Batch API
Image input
Prompt caching

Full feature support

Good for

Cost-efficient thinking
Well-rounded capabilities
Agentic tool use

Replaced by

Gemini 3.8 Flash$1.50 / $7.50

This model: $0.30 / $2.50 per 1M tokens

Compare side by side

Overview

Google · 09Flash

Gemini 2.5 Flash

Our best model in terms of price-performance, offering well-rounded capabilities

Cost: $0.30 in
Context: 1M

Input / output: $0.30 / $2.50
Max output: 64K
Knows up to: January 2025
Released: 17 Jun 2025

Google's first fully hybrid reasoning model: developers can turn thinking on or off and set thinking budgets to trade off quality, cost and latency. The card also covers 2.5 Flash's native image and audio outputs. p.2

gemini-2.5-flash

Input / output per 1M: $0.30 / $2.50
Context window: 1M
Max output: 64K
Knows up to: January 2025
Reasoning: On 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 Model Card. Every claim carries its source page.