modelbenchmark.io

GPT Mini Latest (GPT-5.6 Luna)

OpenAI · gpt-mini

Compare

Cost-efficient GPT-5.6 model for fast, high-volume workloads

Specification

most-agreed values

Context
1.1M
Max output
128K
Released
2026-07-09
Knowledge cutoff
2026-02-16
Retires
—
Open weights
no
Input
text, image, pdf
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.20
Output
$1.20
Cache read
$0.02
Cache write
$0.25

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
edenai$0.20$1.20$0.02$0.251.1M128K—
kilo$0.75$4.50$0.075—400K128K—
openrouter$0.75$4.50$0.075—400K128K—

Price history

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

DateHostField$/M
2026-09-02edenaiCache read$0.075
2026-10-16edenaiCache read$0.02
2026-09-02openrouterCache read$0.075
2026-09-19openrouterCache read$0.075
2026-10-10openrouterCache read$0.075
2026-09-02edenaiInput$0.75
2026-10-16edenaiInput$0.20
2026-09-02openrouterInput$0.75
2026-09-19openrouterInput$0.75
2026-10-10openrouterInput$0.75
2026-09-02edenaiOutput$4.50
2026-10-16edenaiOutput$1.20
2026-09-02openrouterOutput$4.50
2026-09-19openrouterOutput$4.50
2026-10-10openrouterOutput$4.50

More from OpenAI

most-hosted first