← Models

GPT-5.2-Codex

OpenAI · GPT-5

Earlier GPT-5 Codex variant retained as historical context after GPT-5.3-Codex.

Part of GPT family · Other versions: GPT-5.3-Codex , GPT-5.3 , GPT-5.4-Pro , GPT-5.4 , GPT-5.2-Pro , GPT-5.2 , GPT-5-Codex , GPT-5 nano , GPT-5 mini , GPT-5 , GPT-4.1 , GPT-4o mini Transcribe , GPT-4o mini TTS , GPT-4o Transcribe , GPT-4o mini , GPT-4o
Type
language
Context
400K tokens
Max Output
128K tokens
Status
legacy
Input
$1.5/1M tok
Output
$6/1M tok
API Access
Yes
License
proprietary
coding agentic software-engineering tool-use code-review refactoring
Released February 2026 · Updated March 6, 2026

Overview

Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on February 26, 2026.

GPT-5.2-Codex was OpenAI’s coding-specialized GPT-5 variant before the March 2026 refresh to GPT-5.3-Codex. It remains useful as a historical reference point for Codex pricing and capability evolution, but it is no longer the newest Codex entry in the family.

Capabilities

GPT-5.2-Codex is built for multi-file edits, refactors, test-aware implementation loops, and code review assistance. It tends to perform best when prompts include explicit acceptance criteria, repository conventions, and validation constraints.

Technical Details

OpenAI documentation lists GPT-5.2-Codex with a 400K context window and 128K maximum output. It is available through the same modern API surfaces used for tool-calling and structured orchestration, which makes it practical for CI-adjacent agent workflows.

Pricing & Access

Published API pricing (per 1M tokens):

  • Input: $1.50
  • Output: $6.00

This pricing profile is optimized for coding workflows with significant output volume compared with general GPT-5 tiers.

Best Use Cases

Use this page as a historical reference. For new coding-agent builds and repository-scale implementation workflows, prefer GPT-5.3-Codex.

Comparisons

  • GPT-5.3-Codex (OpenAI): Current Codex successor in the GPT-5 family.
  • GPT-5.4 (OpenAI): Broader high-end choice for mixed coding and reasoning workloads.
  • Claude Opus 4.6 (Anthropic): Strong alternative for coding-heavy workflows outside the OpenAI stack.