Gemini 2.5 Flash

GoogleFast

Fast and cost-efficient with thinking capabilities. Great balance of speed and intelligence. Tiered pricing: $0.15/M input (<=200K ctx), $0.30/M (>200K); $0.60/M output (<=200K), $1.20/M (>200K).

Pricing

Input (per 1M tokens)
$0.15
Output (per 1M tokens)
$0.60

Cost Examples

ScenarioCost
100 chat messages (500 in / 200 out each)$0.0195
1K API calls (2K in / 500 out each)$0.6000
10K short requests (200 in / 100 out each)$0.9000
1M tokens input + 100K output$0.2100

Capabilities

Context Window
1.0M
Max Output
66K
Speed
150 tok/s
Released
2025-04-17
YesVision
YesTool Use
YesStreaming
YesJSON Mode

API Details

Model IDgemini-2.5-flash
API Endpointhttps://generativelanguage.googleapis.com/v1beta/models
Last Updated2026-04-12

Other Google Models

Gemini 2.5 ProFlagship
$1.25 in / $10.00 out per 1M tokens
Gemini 2.0 FlashFast
$0.10 in / $0.40 out per 1M tokens
Open Cost Calculatorto compare Gemini 2.5 Flash costs with other models