modelbenchmark.io

Gemini Flash Latest

Google · gemini-flash

Compare

High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning

Specification

google listing

Context
1M
Max output
66K
Released
2026-08-13
Knowledge cutoff
2026-03
Retires
Open weights
no
Input
text, image, video, audio, pdf
Output
text

Price

US dollars per million tokens · google list price

Input
$0.75
Output
$3.75
Cache read
$0.075
Cache write
$0.075

Rate limits

as listed

Requests per minute
15
Tokens per minute
250,000

Available from 10 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
googlevendor$0.75$3.75$0.0751M66K
vertex_ai-language-modelsfreefree1M8K
gemini$0.30$2.50$0.031M66K
orcarouter$0.50$3.00$0.101M66K
edenai$0.75$3.75$0.075$0.04171M66K
kilo$0.75$3.75$0.075$0.04171M66K
nano-gpt$0.75$3.75$0.075$0.0751M66K
openrouter$0.75$3.75$0.075$0.04171M66K
google-vertex$1.50$9.00$0.151M66K
merge-gateway$1.50$9.00$0.151M66K

Price history

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

DateHostField$/M
2026-09-02nano-gptCache read$0.0375
2026-09-02nano-gptCache read$0.075
2026-09-02nano-gptCache write$0.0208
2026-09-02nano-gptCache write$0.075
2026-09-02nano-gptInput$0.375
2026-09-02nano-gptInput$0.75
2026-09-02nano-gptOutput$1.875
2026-09-02nano-gptOutput$3.75

More from Google

most-hosted first