Cracked AI Engineering

Gemini Flash Latest vs Gemini 2.5 Flash Preview 05-20

Choose Gemini 2.5 Flash Preview 05-20 for cost-effective AI development with its lower pricing of $0.15/M input and $0.6/M output tokens. While both models offer a context window of 1,048,576 tokens and advanced reasoning capabilities, Gemini Flash Latest is better suited for cutting-edge applications with its $0.3/M input and $2.5/M output tokens pricing. Decide based on your budget and project requirements.

Quick Overview

Gemini Flash Latest

Vertex

1.0M tokens context • $0.30 / $2.50 per 1M tokens

View full specifications →

Gemini 2.5 Flash Preview 05-20

Vertex

1.0M tokens context • $0.15 / $0.60 per 1M tokens

View full specifications →

Detailed Comparison

Specification
Gemini Flash Latest
Gemini 2.5 Flash Preview 05-20
Provider
Vertex
Vertex
Context Window
1.0M tokens
1.0M tokens
Max Output Tokens
66K tokens
66K tokens
Input Pricing (per 1M tokens)
$0.30
$0.15
Output Pricing (per 1M tokens)
$2.50
$0.60
Release Date
Sep 2025
May 2025

Capabilities

Capability
Gemini Flash Latest
Gemini 2.5 Flash Preview 05-20
Text Generation
Vision
Audio Input
Video Understanding
PDF Processing
Function Calling
Advanced Reasoning
File Attachments

Which Model Should You Choose?

Choose Gemini Flash Latest if:

    Choose Gemini 2.5 Flash Preview 05-20 if:

    • • Cost efficiency is a priority