modelbenchmark.io

Codex Mini

OpenAI · codex-mini

Compare

Coding-optimized GPT model for repository edits, reviews, and agentic software work

Specification

most-agreed values

Context
200K
Max output
100K
Released
2025-05-16
Knowledge cutoff
2024-04
Retires
2026-11-15
Open weights
no
Input
text, image, pdf
Output
text

Price

US dollars per million tokens · most-agreed

Input
$1.50
Output
$6.00
Cache read
$0.375

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
azure
$1.50
$1.65
$6.00
$6.60
$0.375
$0.413
—200K100K2026-11-15
azure_ai$1.50$6.00$0.375—200K100K2026-11-15
azure-cognitive-services$1.50$6.00$0.375—200K100K—

Price history

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

DateHostField$/M
2026-09-02azureCache read$0.375
2026-09-17azureCache read$0.375
2026-09-02azureInput$1.50
2026-09-17azureInput$1.50
2026-09-02azureOutput$6.00
2026-09-17azureOutput$6.00

More from OpenAI

most-hosted first