modelbenchmark.io

Gemini 2.5 Flash 0520 Thinking

Google · gemini-2-5-flash-preview-05-20

Compare

Preview snapshot of Gemini 2.5 Flash with controllable thinking budgets

Specification

most-agreed values

Context
1M
Max output
66K
Released
2025-05-20
Knowledge cutoff
2025-01
Retires
—
Open weights
no
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.15
Output
$3.50
Cache read
$0.015

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
jiekou$0.1425$3.325$0.0285—1M66K—
nano-gpt$0.15$0.60$0.015—1M66K—
nano-gpt · thinking$0.15$3.50$0.015—1M66K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02jiekouInput$0.135
2026-10-22jiekouInput$0.1425
2026-09-02jiekouOutput$3.15
2026-10-22jiekouOutput$3.325

More from Google

most-hosted first