🔍 Read the full analysis: From Model Retirement To Migration: OpenAI’s GPT-4o, GPT-4.1, And GPT-5-nano on ThorstenMeyerAI.com
Get business pricing on office and shipping supplies
- Business-only prices and quantity discounts
- Tax-exempt purchasing
- Multiple users, one account, clear invoices
TL;DR
OpenAI’s deprecation schedule, as reported by ThorstenMeyerAI.com on Nov. 1, 2026, lists GPT-5, GPT-5 mini and GPT-5-nano for API retirement on Dec. 11, followed by GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini on Jan. 14, 2027. The report names replacement models and flags changes to pricing, reasoning behavior and model instructions that developers should test before migrating.
OpenAI plans to retire GPT-5, GPT-5 mini and GPT-5-nano from its API on Dec. 11, 2026, followed on Jan. 14, 2027, by GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini. The dates and replacement recommendations were summarized by ThorstenMeyerAI.com on Nov. 1 from OpenAI’s deprecations page; the changes affect developers whose applications call those model IDs, not just people using ChatGPT.
According to the report, OpenAI lists GPT-5.6 Sol as the replacement for GPT-5 and o3, GPT-5.6 Terra for GPT-5 mini, and GPT-5.6 Luna for GPT-5-nano. GPT-5-pro and o3-pro are also scheduled to move to GPT-5.6 Sol with its pro reasoning mode. The report says the GPT-4o and GPT-4.1 models scheduled for January are directed to GPT-6 Luna.
Some model IDs had already been shut down on Oct. 23, 2026, including GPT-4.1-nano, the original GPT-4o snapshot, GPT-4 Turbo, GPT-3.5 Turbo, o1 and o4-mini. The article says calls still using those IDs may fail. It also lists a separate Nov. 30 shutdown for OpenAI’s Evals platform, Agent Builder and reusable prompt objects; existing evals became read-only on Oct. 31.
The report warns that replacement does not mean identical behavior or cost. It gives standard per-million-token prices checked Nov. 1: GPT-4o at $2.50 input and $10 output versus GPT-6 Luna at $0.10 input and $0.50 output. By contrast, the stated GPT-5-nano to GPT-5.6 Luna move raises listed input pricing from $0.05 to $0.20 and output pricing from $0.40 to $1.20. These are reported prices, not a forecast of any particular application’s bill.
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 Can Change Cost and Output
For businesses, the API schedule turns model retirement into a maintenance deadline: an old model ID embedded in code or an automation can stop working when its shutdown date arrives. Migrating early gives teams time to locate dependencies, compare outputs and update monitoring rather than discovering a failure through users.
The change may also affect budgets and application behavior. ThorstenMeyerAI.com describes the listed replacements as reasoning models, for which hidden reasoning tokens are billed as output. The report also cautions that some sampling parameters may need to be removed and that a tight output limit can produce an empty, billed response. Those observations make testing prompts, token limits and price assumptions part of migration work, not just swapping a model name.
OpenAI’s updated Model Spec adds a separate behavioral consideration. The report says the Oct. 29 version removes much of the detailed style guidance, including a default preference for Markdown. Applications that require a particular structure should specify it directly and test whether the response follows that instruction.
Products Worth Considering
Samsung 49-inch Odyssey OLED G9 (G91SD) Dual QHD Curved Gaming Monitor
LG UltraGear 34GX90SA-W 34-inch WQHD Curved OLED Gaming Monitor
Samsung 49-Inch Odyssey G93SC QD-OLED Curved Gaming Monitor
As an affiliate, we earn on qualifying purchases.
API Dates Differ From ChatGPT
This schedule concerns API access, which developers use to power their own products and internal tools. The report says OpenAI had already removed GPT-4o, GPT-4.1 and GPT-4.1 mini from ChatGPT on Feb. 13, 2026. That earlier consumer-facing change is distinct from the API retirements now scheduled for December and January.
The article says its dates were checked against OpenAI’s deprecations page on Nov. 1, 2026, and that OpenAI says it emails affected customers and documents deprecations there. It also reports that fine-tuned models follow their base model’s shutdown schedule and that the named replacement models do not support fine-tuning. Developers using fine-tuned versions may therefore need a different migration plan from users of standard model IDs.
OpenAI’s page reportedly promises at least six months’ notice for generally available models unless safety or compliance concerns require a faster timeline. The report notes that the Jan. 14 date was announced on Oct. 14, a three-month interval, but says the notice entry does not explain which rule applies. It also says some customers may be able to purchase dedicated capacity to retain access after shutdown.
“If your app depends on a format, say so in the request.”
— ThorstenMeyerAI.com
Pricing and Notice Need Checking
The schedule and prices in this article come from a third-party report’s review of OpenAI pages, rather than a direct statement included here from OpenAI. Pricing may change, and the figures cited are short-context prices for prompts up to 272,000 tokens, checked on Nov. 1. Actual spending will depend on usage, caching, output length and applicable pricing terms.
It is also not clear from the report why the January GPT-4o and GPT-4.1 shutdown notice spans three months despite the stated six-month notice policy for generally available models. OpenAI’s reason for the timing, whether a particular exception applies, and the terms for dedicated capacity are not specified. Developers should verify their account-specific notices and contracts with OpenAI.
The report does not provide independent benchmark results showing that each replacement will match the retired model on a particular task. The precise impact on an application’s accuracy, latency, formatting and costs remains dependent on testing.
Audit IDs Before Each Deadline
Developers should first search source code, configuration files, workflow tools and evaluation setups for every retired model ID, including dated snapshots and fine-tuned versions. Calls to models already shut down on Oct. 23 should be investigated now; the next reported milestone is Nov. 30, when Evals, Agent Builder and reusable prompt objects are scheduled to close.
Before the Dec. 11 and Jan. 14 API dates, teams can run representative prompts against the recommended replacement, compare task results and required formats, and check token limits and output billing. They should also confirm the current deprecation schedule, pricing and account notices on OpenAI’s own pages, since the report says prices and dates can require verification.
Key Questions
When are GPT-5-nano and GPT-5 mini scheduled to leave the API?
The report lists Dec. 11, 2026 for GPT-5-nano and GPT-5 mini, alongside GPT-5 and several other models.
When are GPT-4o and GPT-4.1 models scheduled for retirement?
The reported date is Jan. 14, 2027 for the listed GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini snapshots.
Which models does the report name as replacements?
It names GPT-5.6 Sol, Terra and Luna for retiring GPT-5-family models, and GPT-6 Luna for the listed GPT-4o and GPT-4.1 models. Check OpenAI’s current documentation before changing production systems.
Will a replacement have the same cost and behavior?
Not necessarily. The report gives different per-token prices for several migrations and describes the replacements as reasoning models, with possible changes to output billing, parameters and response formatting. Teams should test their own workloads.
Does this schedule mean GPT-4o is being removed from ChatGPT now?
No. The report says GPT-4o and other listed models were already removed from ChatGPT on Feb. 13, 2026; the current dates discussed here concern API model access.
Source: ThorstenMeyerAI.com
