Head to head

Gemini 2.5 Flash-Lite vs GPT-4.1 nano

On a blended workload of one million input tokens and three million output tokens, GPT-4.1 nano is line-ball with Gemini 2.5 Flash-Lite.

Gemini 2.5 Flash-LiteGPT-4.1 nano
Provider Google OpenAI
Input / MTok $0.1 $0.1
Output / MTok $0.4 $0.4
Cache read / MTok $0.01 $0.025
Context window 1,047,576
Blended 1M in + 3M out $1.30 $1.30
Status ga ga

Gemini 2.5 Flash-Lite detail   GPT-4.1 nano detail