modelbenchmark.io

Gemini 2.5 Flash Preview (09/2025) – Thinking

Google · gemini-2-5-flash-preview-09-2025-thinking

Compare

Compact GPT model for low-latency assistance and high-volume workloads

Specification

most-agreed values

Context
1M
Max output
66K
Released
2025-09-25
Knowledge cutoff
Retires
Open weights
no
Input
text, image, audio, pdf
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.30
Output
$2.50
Cache read
$0.03

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt$0.30$2.50$0.031M66K

More from Google

most-hosted first