Gemini 2.5 Flash Lite (8B)

Google

Gemini 2.5 Flash Lite (8B) is the most cost-effective model with nearly unlimited free tier quota.

Text Generation API Gemini Family v2.5-flash-8b
Documentation Back to Models
Parameters
-
params
Context Window
1.0M
tokens
Max Output
8K
tokens
Input Price
$0.0375
per 1M tokens
Output Price
$0.1500
per 1M tokens

Gemini Family Timeline 12 versions

Gemini 3.1 Flash-Lite api
Mar 2026
Gemini 3.1 Pro Latest api
Feb 2026
Gemini 3.0 Ultra api
Nov 2025
Gemini 3.0 Flash api
Oct 2025
Gemini 3.0 Pro api
Oct 2025
Gemini 2.5 Flash Lite (8B) Current api
May 2025
Gemini 2.5 Flash api
Apr 2025
Gemini 2.5 Pro api
Mar 2025
Gemini 2.0 Flash Exp api
Dec 2024
Gemini 1.5 Pro api
May 2024
Gemini 1.5 Flash api
May 2024
Gemini 1.5 Pro (Vertex) api
-

Capabilities

👁️
Vision
⚡
Function Calling
📋
JSON Mode
🌊
Streaming
💬
System Prompt
🖥️
Code Execution
🔍
Web Search
🔌
MCP Support

Extended Pricing

Input
$0.0375/1M
Output
$0.1500/1M
Cache Read
$0.0100/1M
Cache Write
$0.0375/1M

Details

Release Date
May 20, 2025
Knowledge Cutoff
August 1, 2024
Source
API
API Key Required
Yes
License
Proprietary
Model ID
gemini-2.5-flash-8b
Last updated: November 1, 2025