🔍 Read the full analysis: How To Avoid Disruption As OpenAI Switches Off GPT-4o, GPT-4.1, And GPT-5-nano on ThorstenMeyerAI.com
Get the little things that make your day delivered free with Prime
- Fast, free delivery on millions of items
- Prime Video, Amazon Music and more included
- Member-only deals all year
TL;DR
OpenAI’s published deprecation schedule lists API shutdowns on Dec. 11, 2026, and Jan. 14, 2027, affecting GPT-5 models and GPT-4o and GPT-4.1 snapshots. Developers should inventory model IDs, check replacement pricing and behavior, and test before switching; some older IDs have already been shut down.
OpenAI plans to retire several models from its API, with GPT-5, GPT-5 mini and GPT-5-nano scheduled to leave on Dec. 11, 2026, and listed GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini snapshots on Jan. 14, 2027. The dates matter to companies running applications and automations that call those model IDs: affected requests may stop working unless developers migrate and test them.
OpenAI’s deprecation page, as checked by ThorstenMeyerAI.com on Nov. 1, lists gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro, o3 and o3-pro for shutdown on Dec. 11. The listed replacement models are from the GPT-5.6 family. OpenAI says fine-tuned versions follow their base model’s shutdown schedule; the article says the recommended replacements do not support fine-tuning.
The Jan. 14 list includes dated snapshots of GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini. The source says OpenAI recommends gpt-6-luna for these models. It also reports that several IDs, including gpt-4.1-nano, the original GPT-4o snapshot, gpt-4-turbo, gpt-3.5-turbo, o1 and o4-mini, were already shut down on Oct. 23. Applications still calling those IDs may already encounter failures.
The source warns that migration involves more than changing a model name. Listed replacements are reasoning models, which may use hidden reasoning tokens billed as output. Some sampling parameters may need to be removed, and a restrictive output-token limit can result in an empty answer that is still billed, according to the article. Pricing also varies: its Nov. 1 comparison lists GPT-4o at $2.50 per million input tokens and $10 per million output tokens, versus $0.10 and $0.50 for gpt-6-luna. By contrast, the listed move from GPT-5-nano to GPT-5.6-luna raises the input price from $0.05 to $0.20 and output from $0.40 to $1.20 per million tokens.
Infographic 01 · The shutdown calendar
What stops working, and when
OpenAI's API deprecations, as listed on 1 November 2026. GPT-4o and GPT-4.1 already left ChatGPT on 13 February 2026; this round is about apps built on the API.
- 23 Oct 2026Already offAlready shut down
gpt-3.5-turbo,gpt-4,gpt-4-turbo,gpt-4.1-nano,gpt-4o-2024-05-13,o1,o1-pro,o3-mini,o4-mini,gpt-image-1. Calls to these fail today. - 30 Nov 2026Your testsEvals platform, Agent Builder, reusable prompts
Not models, but tools many teams test with. Existing evals became read-only on 31 Oct. Export them first.
- 11 Dec 2026Notified 11 JunGPT-5 family and o3
gpt-5→gpt-5.6-sol·gpt-5-mini→gpt-5.6-terra·gpt-5-nano→gpt-5.6-luna·o3→gpt-5.6-sol·gpt-5-pro,o3-pro→gpt-5.6-sol(pro mode) - 14 Jan 2027Notified 14 OctGPT-4o, GPT-4o mini, GPT-4.1, GPT-4.1 mini
Snapshots
gpt-4o-2024-08-06,gpt-4o-2024-11-20,gpt-4o-mini-2024-07-18,gpt-4.1-2025-04-14,gpt-4.1-mini-2025-04-14→gpt-6-luna. Fine-tuned versions follow their base model. - Jan to Apr 2027Plan aheadAudio, speech, older GPT-5.x
6 Jan:
tts-1and others · 20 Jan: older audio and realtime models · 26 Feb:whisper-1, GPT-4o transcription · 1 Apr:gpt-5.1,gpt-5.4-nano,gpt-5.3-codex
Sources: OpenAI deprecations page (checked 1 Nov 2026) · OpenAI Help Center, model release notes. Dates as listed by OpenAI; shutdowns can be rescheduled.
Powered by Thorsten Meyer AI
Migration Risks for API Users
The shutdowns affect software built on OpenAI’s API, not just people selecting a model in a chat interface. A model ID can be embedded in an application configuration, a test, or a no-code workflow and remain unnoticed until a request fails. A missed migration could interrupt customer-facing features, internal tools or automated processes.
Replacing the ID may also change costs and response behavior. The source’s price examples show that some migrations could lower listed token rates while others raise them. Reasoning-model billing and different parameter requirements could affect both budgets and output formats. Teams need to test representative tasks and calculate expected usage rather than assume a replacement behaves or costs the same.
Products Worth Considering
Levoit Core 400S-P Smart Air Purifier for Large Rooms
LEVOIT Vital 200S-P Smart Air Purifier for Large Rooms
Withings BPM Connect Wi-Fi and Bluetooth Blood Pressure Monitor
As an affiliate, we earn on qualifying purchases.
Published Dates and Model Changes
The schedule summarized by ThorstenMeyerAI.com gives two main upcoming dates: Dec. 11, 2026, for specified GPT-5 and o-series models, and Jan. 14, 2027, for listed GPT-4o and GPT-4.1 snapshots. The source says affected customers are emailed and that OpenAI documents deprecations on its schedule. Developers should check the current official page and their own account notices because the schedule and prices can change.
The article distinguishes the API changes from an earlier ChatGPT change. It reports that GPT-4o, GPT-4.1 and GPT-4.1 mini left ChatGPT on Feb. 13, 2026; the current dates concern API access and applications built with it. The source also reports that OpenAI’s Oct. 29 Model Spec revision removed much of its detailed style guidance, including a default preference for Markdown. That does not itself set the API shutdown dates, but it makes explicit formatting instructions and output testing relevant for teams relying on a particular style.
Another operational date is Nov. 30, 2026, when the source says OpenAI plans to shut down its Evals platform, Agent Builder and reusable prompt objects. It reports existing evals became read-only on Oct. 31. Teams using those tools may need to account for that change while planning model migration tests.
Open Questions on Timing and Behavior
The source says the Jan. 14 shutdown notice was issued on Oct. 14, while OpenAI’s deprecation page promises at least six months’ notice for generally available models, subject to faster action for safety or compliance concerns. The interval described is three months. The cited entry does not explain which notice rule applies, so developers with contractual commitments or committed spend may want to ask their OpenAI account team.
The article does not provide a complete inventory of every affected account, application or contractual exception. It says some customers may be able to buy dedicated capacity for continued access after shutdown, but does not set out eligibility or terms. Actual migration costs will depend on request volume, prompt length, cached input and output use; the cited prices are a snapshot, not a forecast. Teams also need to verify how replacements perform on their own workloads, since the source’s cautions do not establish that every application will produce an empty answer or a different result.
Steps Before the Shutdown Dates
Developers can start by searching source code, configuration files, tests and no-code workflows for every model ID and dated snapshot in use. Check logs and account-level usage as well: a model name may be specified outside the main application code. Compare the findings with OpenAI’s current deprecation page and notices, particularly for IDs already listed as shut down.
Next, test each proposed replacement against real tasks before changing production traffic. Include normal and unusually long prompts, structured-output requirements, tool use and cases with low output limits. Confirm any sampling parameters still supported, inspect whether outputs preserve required formatting, and measure latency, failure rates and token use. Run a price estimate using current official rates and expected input, output and cached-token volumes.
Teams should schedule a staged rollout with monitoring and a documented fallback plan where available, then retest after changes. OpenAI’s listed dates are Dec. 11, 2026, and Jan. 14, 2027; the source’s schedule also includes a Nov. 30 shutdown for named developer tools. The official schedule, account communications and contractual terms are the places to verify any later updates or access options.
Key Questions
Which OpenAI API models are scheduled to shut down first?
The schedule reported by ThorstenMeyerAI.com lists gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro, o3 and o3-pro for Dec. 11, 2026. Some older model IDs were listed as shut down on Oct. 23, 2026.
When are the listed GPT-4o and GPT-4.1 snapshots scheduled to go?
The source lists specified GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini snapshots for Jan. 14, 2027. Check OpenAI’s current deprecation page to confirm the status of the exact ID your application uses.
Will changing the model ID be enough?
Not necessarily. The source says recommended replacements are reasoning models and may handle parameters, output limits, billing and response formatting differently. Test the replacement against your application’s requirements before deployment.
Could the replacement cost more?
Yes. In the source’s Nov. 1 price comparison, GPT-4o’s listed replacement, gpt-6-luna, costs less per million input and output tokens, while the listed GPT-5-nano replacement, gpt-5.6-luna, costs more. Prices can change, so check current rates and estimate your own usage.
What should teams do now?
Inventory model IDs across code and workflows, check OpenAI’s latest notices, test listed replacements on representative requests, review pricing and output behavior, and plan a monitored migration before the applicable shutdown date.
Source: ThorstenMeyerAI.com
