← Models

GPT-5.2-Codex

OpenAI · GPT-5

Deprecated GPT-5.2 Codex compatibility route scheduled for API shutdown on July 23, 2026.

Part of GPT family · Other versions: GPT-5.6 Luna , GPT-5.6 Terra , GPT-5.6 Sol , GPT-5.5 Pro , GPT-5.5 , GPT-Rosalind , GPT-5.4 mini , GPT-5.4 nano , GPT-5.4 Pro , GPT-5.4 , GPT-5.3 , GPT-5.3-Codex , GPT-5.2 Pro , GPT-5.2 , GPT-5-Codex , GPT-5 mini , GPT-5 nano , GPT-5 , GPT-4.1 , GPT-4o mini Transcribe , GPT-4o mini TTS , GPT-4o Transcribe , Computer Use Preview , GPT-4o mini , GPT-4o
Type
language
Context
400K tokens
Max Output
128K tokens
Status
deprecated
Input
$1.75/1M tok
Output
$14/1M tok
API Access
Yes
License
proprietary
coding agentic software-engineering tool-use code-review refactoring deprecated
Released December 2025 · Updated July 10, 2026

Overview

Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on July 10, 2026.

GPT-5.2-Codex is a deprecated Codex-specialized compatibility route. OpenAI’s API deprecation table schedules it for shutdown on July 23, 2026 and names GPT-5.5 as the direct replacement. It remains relevant only for teams completing a migration from existing coding-agent prompts or evaluation harnesses; new work should begin from current OpenAI Codex and GPT-5.6 guidance.

Capabilities

GPT-5.2-Codex was built for multi-file edits, refactors, test-aware implementation loops, and code review assistance. Its remaining practical use is compatibility testing during an active migration before the shutdown date.

Technical Details

OpenAI’s current model card lists GPT-5.2-Codex with a 400K context window, 128K max output, and reasoning effort controls from low through xhigh. Treat those numbers as compatibility data for older direct API routing, not proof that this is the newest Codex-linked route.

This is now historical compatibility data rather than a current deployment recommendation. OpenAI also lists GPT-5.2 as deprecated in Codex when using ChatGPT sign-in.

Pricing & Access

Published API pricing (per 1M tokens):

  • Input: $1.75
  • Cached input: $0.175
  • Output: $14.00

This pricing profile describes the route before shutdown. Migration budgets should compare the documented replacement with GPT-5.6 and the current Codex product surface rather than plan new usage around this older model.

Best Use Cases

Use GPT-5.2-Codex only for compatibility checks and migration validation before July 23, 2026. Do not start fresh deployments on it.

Comparisons

  • GPT-5.3-Codex (OpenAI): Better current explicit Codex-model reference for coding-heavy workflows.
  • GPT-5.2 (OpenAI): Better choice when coding is only part of a broader professional workflow.
  • Claude Opus family (Anthropic): Strong alternative for premium coding-heavy workflows outside the OpenAI stack.