modelbenchmark.io

o3-mini-high

OpenAI · o3-mini-high

Compare

Smaller o-series reasoner for economical coding, math, and planning tasks

Specification

most-agreed values

Context
200K
Max output
100K
Released
2024-12-20
Knowledge cutoff
2024-05
Retires
—
Open weights
no
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.99
Output
$4.00
Cache read
$0.55

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
poe$0.99$4.00——200K100K—
nano-gpt$1.10$4.40$0.55—200K100K—

Price history

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

DateHostField$/M
2026-09-02openrouterCache read$0.55
2026-09-06openrouterCache read$0.55
2026-10-10openrouterCache read$0.55
2026-09-02openrouterInput$1.10
2026-10-10openrouterInput$1.10
2026-09-02openrouterOutput$4.40
2026-10-10openrouterOutput$4.40

More from OpenAI

most-hosted first