---
schema: 1
type: term
title: '**Codex 1**'
description: >-
  **Codex 1** is the custom model powering OpenAI's Codex coding agent — a tuned
  version of o3, trained to produce reviewable diffs, honest summaries, and
  deterministic log citations.[^ceebdf5b-d543-5073-becc-f4bfbb1dcabf@382]
canonical: 'https://liquidgold.cc/channel/everyinc/explore/term/codex-1-6392635c51c3'
markdown: 'https://liquidgold.cc/channel/everyinc/explore/term/codex-1-6392635c51c3.md'
llms: null
parent: 'https://liquidgold.cc/channel/everyinc/llms.txt'
channel: everyinc
updated: '2026-10-23T22:12:35.346Z'
language: null
children: []
---


# \*\*Codex 1\*\*

Canonical: https://liquidgold.cc/channel/everyinc/explore/term/codex-1-6392635c51c3

Parent: [Channel index](https://liquidgold.cc/channel/everyinc/llms.txt)

## Definition

**Codex 1** is the custom model powering OpenAI's Codex coding agent — a tuned version of o3, trained to produce reviewable diffs, honest summaries, and deterministic log citations.[^ceebdf5b-d543-5073-becc-f4bfbb1dcabf@382]

In the captured interview with OpenAI's Codex product team, **Codex 1** is introduced as the custom model powering OpenAI Codex — a **tuned version of o3** trained specifically for agentic coding work.[^ceebdf5b-d543-5073-becc-f4bfbb1dcabf@382] It is the model behind the interview's central claims about Codex's behavior: producing **reviewable diffs**, writing **honest summaries**, and supplying **deterministic log citations** so a human can verify what the agent actually did.[^ceebdf5b-d543-5073-becc-f4bfbb1dcabf@382] The interview frames Codex 1 not as a general chat model but as one shaped for a **delegation-first** workflow: tasks are handed off whole, run in a locked-down container, and come back as changes a developer can inspect rather than conversations to babysit. The tuning goal is trust through verifiability — the model's output is meant to be checked, not taken on faith.[^ceebdf5b-d543-5073-becc-f4bfbb1dcabf@382]