modelbenchmark.io

GPT 5.3 Codex (Fast)

OpenAI · gpt-5-3-codex-fast

Compare

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

Specification

most-agreed values

Context
400K
Max output
128K
Released
2026-02-05
Knowledge cutoff
2025-08-31
Retires
Open weights
no
Input
text, image, pdf
Output
text

Price

US dollars per million tokens · most-agreed

Input
$3.50
Output
$28.00
Cache read
$0.35

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
vercel$3.50$28.00$0.35400K128K

More from OpenAI

most-hosted first