GadgetBond

  • Latest
  • Features
  • How-to
  • Tech
    • AI
      • Apple Intelligence
      • Gemini AI
      • Google DeepMind
      • Anthropic
      • Claude AI
      • Claude Code
      • OpenAI
      • ChatGPT
      • Codex
      • Perplexity
      • SpaceXAI
      • Grok AI
      • Microsoft Copilot
      • Meta AI
    • Amazon
    • Apple
    • CES
    • Computing
    • Creators
    • Google
    • Meta
    • Microsoft
    • Mobile
    • NVIDIA
    • Samsung
    • Security
    • Smart Home
    • Sony
    • Xbox
    • YouTube
  • Transportation
    • Audi
    • BMW
    • Cadillac
    • E-Bike
    • Ferrari
    • Ford
    • Honda Prelude
    • Lamborghini
    • McLaren
    • Mercedes
    • Porsche
    • Rivian
    • Tesla
  • Culture
    • Gaming
    • Streaming
    • Apple TV
    • Disney
    • Hulu
    • Marvel
    • HBO Max
    • Netflix
    • Paramount
    • SHOWTIME
    • Spotify
    • Star Wars
Add GadgetBond as a preferred source to see more of our stories on Google.
Font ResizerAa
GadgetBondGadgetBond
  • Latest
  • Tech
  • AI
  • Features
  • Deals
  • How-to
  • Apps
  • Computing
  • Gaming
  • Mobile
  • Streaming
  • Transportation
Search
  • Latest
  • Deals
  • Buying Guide
  • How-to
  • Features
  • Tech
    • Amazon
    • Apple
    • CES
    • Computing
    • Creators
    • Google
    • Meta
    • Microsoft
    • Mobile
    • NVIDIA
    • Samsung
    • Security
    • Smart Home
    • Sony
    • Xbox
    • YouTube
  • AI
    • Apple Intelligence
    • Gemini AI
    • Google DeepMind
    • Anthropic
    • Claude AI
    • Claude Code
    • OpenAI
    • ChatGPT
    • Codex
    • Perplexity
    • SpaceXAI
    • Grok AI
    • Microsoft Copilot
    • Meta AI
  • Transportation
    • Audi
    • BMW
    • Cadillac
    • E-Bike
    • Ferrari
    • Ford
    • Lamborghini
    • McLaren
    • Mercedes
    • Porsche
    • Rivian
    • Tesla
  • Culture
    • Gaming
    • Streaming
    • Apple TV
    • Disney
    • Hulu
    • Marvel
    • HBO Max
    • Netflix
    • Paramount
    • SHOWTIME
    • Spotify
    • Star Wars
Follow US
AIOpenAITech

OpenAI Codex loses six older models in spring cleanup

OpenAI is quietly trimming six older Codex models, leaving developers with a tighter, more modern lineup centered on GPT‑5.4.

By
Shubham Sawarkar
Shubham Sawarkar's avatar
ByShubham Sawarkar
Editor-in-Chief
Shubham Sawarkar is a technology journalist at GadgetBond, covering Apple, AI, consumer technology, software, gadgets, and product launches. His work explores emerging technologies, industry developments, product...
Follow:
- Editor-in-Chief
Apr 8, 2026, 3:05 AM EDT
Share
GadgetBond is reader-supported. We may earn a commission from purchases through our links. Learn more
OpenAI Codex app logo featuring a stylized terminal symbol inside a cloud icon on a blue and purple gradient background, with the word “Codex” displayed below.
Image: OpenAI
SHARE

OpenAI is phasing out a batch of older Codex models on April 14, and gently nudging developers toward a smaller, cleaner lineup built around GPT-5.4 and the newer 5.3‑based coding models. It is less about killing off features and more about collapsing a messy model list into a few workhorses that can handle most coding and “AI pair programmer” tasks on their own.

In a post on X, the OpenAI Developers account announced that when you sign in to Codex with a ChatGPT account after April 14, you’ll no longer see six older options: gpt-5.2-codex, gpt-5.1‑codex-mini, gpt-5.1-codex‑max, gpt-5.1-codex, gpt-5.1, and gpt-5. For anyone who has been relying on these, the key detail is that this change only affects Codex when you log in with ChatGPT; if you really need a retired model, you can still bring your own OpenAI API key and keep using it outside this streamlined Codex picker.

Once the switch flips, the default Codex model lineup under ChatGPT sign‑in will center on gpt-5.4, gpt-5.4-mini, gpt-5.3-codex, gpt-5.3-codex-spark (reserved for Pro users), and gpt-5.2. OpenAI’s own guidance is pretty straightforward: start with gpt-5.4 for most coding tasks, drop to gpt-5.4-mini when you care more about speed and cost than raw depth, and turn to the 5.3‑based Codex models when you want something tuned specifically for code, long‑running software tasks, or ultra‑fast interactive coding sessions.

This deprecation fits into a bigger trend at OpenAI: the company has been slowly pruning older or overlapping models for a few years, including classic Codex APIs in 2023 and several GPT-4 variants more recently, with official documentation that lists timed shutdowns and recommended replacements. The goal is to move everyone toward a smaller set of “frontier” models that do more, cost less per unit of work, and are easier to manage at scale, instead of making developers pick from a long, confusing list of nearly identical options.

On the Codex side, the new generation is clearly built around GPT-5.3-Codex and GPT-5.4. GPT-5.3-Codex is positioned as OpenAI’s “agentic” coding model, designed to handle longer‑horizon jobs like refactoring big codebases, wiring up tools, and running multi‑step plans with minimal hand‑holding. GPT-5.3-Codex-Spark then takes that core and shrinks it into a small, speed‑first model that can answer and edit almost in real time, hitting very high token‑per‑second rates on benchmarks while still solving serious software tasks. GPT-5.4, meanwhile, blends these coding chops into a more general‑purpose reasoning model that is meant to be the new default brain for Codex and other professional workflows, so you do not have to switch models every time you move from debugging to writing docs or planning a new feature.

For everyday Codex users, the most visible change will probably be that the model picker gets simpler. Instead of scrolling past a dozen similar‑sounding 5.1 and 5.2 Codex variants, you will mostly be choosing between “main” (gpt-5.4), “cheaper/faster” (gpt-5.4-mini), and “coding‑specialist” models (5.3-codex and Spark). That design is intentional: OpenAI engineers and community members have pointed out that the new models are meant to fold the strengths of the old ones—speed of mini, depth of max, and the coding intuition of 5.2-codex—into fewer SKUs so the interface can move closer to a single “just use the best one” button.

Still, not everyone is thrilled. In the replies to OpenAI’s announcement, some developers are openly sentimental about models like gpt-5.2 and gpt-5.1-codex-mini, which they say are still excellent for tasks like aggressive prompt compaction or as cheap helper models behind the scenes. Others are worried that 5.3-codex might eventually follow the same path unless there is a clear, equally specialized 5.4/5.5‑era Codex replacement that matches its behavior on tightly scoped coding work. That tension—between stability for existing workflows and the push to consolidate around newer, more capable systems—is now a recurring theme in OpenAI’s deprecation timeline.

Practically, the April 14 change forces anyone with a Codex‑heavy workflow to do a quick audit. If your scripts or internal tools explicitly target one of the outgoing models via Codex’s ChatGPT‑linked interface, you will want to migrate those flows to gpt-5.4, 5.4-mini, or one of the 5.3-Codex variants to avoid surprises. Teams that really depend on a specific retired model can insulate themselves by switching to API‑key‑based access, at least in the short term, but long term, the direction of travel is clear: OpenAI expects serious users to keep moving forward as new frontier models pick up the torch from each old generation.

The broader takeaway is that Codex is quietly shifting from “a catalog of models” to “a single, evolving coding assistant” that just happens to have a few different modes under the hood. The retirement of older Codex models is one more step toward that vision, where the defaults keep getting smarter, faster, and more capable, and the average developer no longer needs to be a model‑selection expert just to ship software.


Discover more from GadgetBond

Subscribe to get the latest posts sent to your email.

Topic:ChatGPTOpenAI Codex
Leave a Comment

Leave a Reply Cancel reply

Most Popular

Apple launches Health AI Usage Study with OpenEvidence to evaluate conversational health tools
Gemini can now analyze your spending with Google Wallet and Plaid integration
Garmin Instinct 3 AMOLED gets a $200 Black Friday discount
Google Sheets now lets you publish a Sheets canvas as a standalone link
Robert Pattinson is officially the next James Bond as Amazon MGM Studios announces new 007

Also Read

A gray rounded-square icon featuring a white hard drive with five vertical vent slots on its front edge, centered against a light blue background.

Apple splits macOS Device Control into two privacy settings

Close-up of the Garmin fēnix 8 AMOLED Sapphire smartwatch featuring a DLC titanium bezel, black silicone band, and vibrant fitness dashboard against a dark background.

Get 25% off the dive-rated Garmin fēnix 8 AMOLED smartwatch with this Early Black Friday deal

Google Chat interface showing a "Project Atlas" scheduling pop-up card with suggested times, attendees, and a "Schedule" button over a message.

Google Chat now lets you schedule meetings with a single click using Gemini

Three Apple HomeView smart displays in different colors and configurations, showcasing the 7-inch screens with a smart home dashboard, FaceTime video call, and personalized photo display.

Apple HomeView goes on sale today for $299 with a 7-inch display and Siri AI

Models wearing Google's new smart glasses collections designed with Warby Parker and Gentle Monster.

Google opens pre-orders for new Gemini-powered smart glasses from Warby Parker and Gentle Monster

Google's smart glasses setup screen displaying responsible-use guidelines, including restrictions against recording without permission, filming in sensitive spaces, and covering or damaging the external recording indicator light.

Google outlines privacy safeguards for its upcoming AI glasses, including anti-tampering recording lights

Google Gemini 4 Hydrogen logo displayed against a blue gradient background, featuring the multicolored Gemini star icon and white product name.

Google launches Gemini 4 Hydrogen for faster coding and everyday AI workflows

Blue gradient cards arranged in a semi-circle reading "Now available globally," "Gemini 4 Hydrogen," and "Now in Google Search" beside a mobile screen.

Google brings Gemini 4 Hydrogen to Search, helping users find more relevant websites

Company Info
  • Homepage
  • Support my work
  • Latest stories
  • Company updates
  • GDB Recommends
  • Daily newsletters
  • About us
  • Contact us
  • Write for GadgetBond
  • Editorial guidelines
Legal
  • Privacy Policy
  • Cookies Policy
  • Terms & Conditions
  • DMCA
  • Disclaimer
  • Accessibility Policy
  • Security Policy
  • Do Not Sell or Share My Personal Information
Socials
Follow US

Disclosure: We love the products we feature and hope you’ll love them too. If you purchase through a link on our site, we may receive compensation at no additional cost to you. Read our ethics statement. Please note that pricing and availability are subject to change.

Copyright © 2026 GadgetBond. All Rights Reserved. Use of this site constitutes acceptance of our Terms of Use and Privacy Policy | Do Not Sell/Share My Personal Information.