🔍 Read the full analysis: OpenAI API Model Changes At A Glance: Timing, Impact, And Migration 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 API deprecation schedule lists model shutdowns on Oct. 23 and further retirements on Dec. 11, 2026, and Jan. 14, 2027. Listed replacements may change costs and response behavior, so developers should check model IDs, test workloads and verify current pricing before migrating.
OpenAI’s API deprecation schedule lists further model retirements for Dec. 11, 2026, and Jan. 14, 2027, after a group of older model IDs stopped working on Oct. 23, according to a schedule checked by ThorstenMeyerAI.com on Nov. 1. Developers using those models in apps, automations or other API integrations may need to change model IDs and test for differences in cost and output before their current models are switched off.
The Dec. 11 retirements include GPT-5, GPT-5 mini, GPT-5 nano, GPT-5 pro, o3 and o3-pro. The listed replacements are GPT-5.6 variants: GPT-5 and o3 map to GPT-5.6 Sol; GPT-5 mini to GPT-5.6 Terra; and GPT-5 nano to GPT-5.6 Luna. GPT-5 pro and o3-pro are listed for GPT-5.6 Sol with its pro reasoning mode.
On Jan. 14, 2027, the schedule lists dated snapshots of GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini. The listed replacement for those models is GPT-6 Luna. The article says the plain-name model pages already carry a “Deprecated” status and advises treating those aliases as covered by the January date. OpenAI’s deprecations page is the source for the dates; users should check it for current status and any account-specific notice.
A further group, including GPT-3.5 Turbo, GPT-4 Turbo, GPT-4.1 nano, the original GPT-4o snapshot, o1, o3-mini and o4-mini, is reported as shut down on Oct. 23, 2026. The source says calls using these IDs may already fail. It also reports that fine-tuned versions follow their base model’s shutdown schedule, while the listed replacements do not support fine-tuning.
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
Replacing a model is not necessarily a drop-in change. The source describes the listed replacements as reasoning models, which can handle requests differently and may affect both latency and token use. It says hidden reasoning tokens are billed as output, that some sampling parameters must be removed, and that a restrictive output-token limit can leave a billed response empty. These are practical risks for services that rely on predictable formatting, cost or response length.
The price comparisons in the source also vary by model. Using listed short-context prices per million tokens, it reports GPT-4o at $2.50 per input million and $10 per output million, compared with $0.10 and $0.50 for GPT-6 Luna. But the listed GPT-5 nano replacement, GPT-5.6 Luna, is priced at $0.20 input and $1.20 output, against $0.05 and $0.40 for GPT-5 nano. GPT-5 mini’s listed move to GPT-5.6 Terra is also more expensive in the cited comparison. These are historical prices checked Nov. 1, not forecasts or guarantees; developers should verify current rates and model-specific usage before budgeting.
Behavior may shift as well. The source says OpenAI’s Oct. 29 Model Spec revision removed much of its detailed style guidance, including a default preference for Markdown formatting, and tells models to follow the intent of instructions. Teams whose software expects a particular structure should request that structure explicitly and validate responses. OpenAI also says its models “do not yet fully reflect” the Spec, so the document is not a guarantee of identical behavior across models.
Popular right now
Breville Bambino Espresso Machine, Brushed Stainless Steel (BES450BSS)
KitchenAid Artisan 5-Qt Tilt-Head Stand Mixer – Dried Rose (KSM150PS)
Ninja CREAMi 7-in-1 Ice Cream Maker, NC299AMZ
As an affiliate, we earn on qualifying purchases.
This schedule concerns the OpenAI API, which powers applications and services built by customers. It is separate from the earlier ChatGPT product change: the source reports that GPT-4o, GPT-4.1 and GPT-4.1 mini were removed from ChatGPT on Feb. 13, 2026. That consumer-facing change does not itself establish the API dates; those are listed separately on OpenAI’s deprecations page.
There are other dates relevant to migration work. The source says OpenAI plans to shut down its Evals platform, Agent Builder and reusable prompt objects on Nov. 30, 2026, with existing evaluations read-only from Oct. 31. It also lists later 2027 retirements for speech, audio, transcription and other models. These deadlines may affect teams that use those products to test or operate API workflows, not only teams changing a text model.
According to the article, OpenAI says it emails affected customers and documents deprecations on its public page. It also says the page promises at least six months’ notice for generally available models unless safety or compliance concerns require a faster schedule. The source notes that the January notice was dated Oct. 14, three months before the scheduled shutdown, and says the entry does not explain which notice rule applies. Customers with contractual commitments are advised to ask their OpenAI account team about their specific terms.
Account Terms and Runtime Behavior
Several operational details remain unsettled in the source material. It does not say why the January API notice appears to provide three months rather than the stated six months for generally available models, or whether a safety, compliance or other exception applies. The source recommends that customers with contracts or committed spend ask their account teams; it does not establish what terms apply to any individual customer.
The listed replacements and prices are a snapshot, not a promise that a migration will preserve an application’s behavior or budget. The source does not provide independent benchmark results, latency comparisons or a complete account of compatibility for every integration. Developers should confirm current model availability, pricing, supported parameters and fine-tuning options in OpenAI’s documentation before changing production systems. The exact effect of the revised Model Spec on any given application is also not established.
Check IDs, Then Test Before Cutover
Teams should first search source code, configuration files, test fixtures and no-code workflows for both dated snapshot IDs and short model names. They can then confirm each ID’s status and scheduled date against OpenAI’s deprecations page, identify the replacement listed for their model, and review whether fine-tuning or other features are supported.
Before switching production traffic, developers should run representative prompts against the replacement and compare output structure, quality, token use, latency and error handling. Tests should check any required JSON or Markdown format explicitly, review sampling parameters, and allow sufficient output-token capacity for reasoning models. Pricing should be checked again using the team’s own workload and the current pricing page. The next listed milestones are the Nov. 30 shutdown of several evaluation and prompt tools, the Dec. 11 model retirements, and the Jan. 14, 2027 GPT-4-family retirements.
Key Questions
Which OpenAI API models are scheduled to retire on Dec. 11, 2026?
The schedule cited by ThorstenMeyerAI.com lists GPT-5, GPT-5 mini, GPT-5 nano, GPT-5 pro, o3 and o3-pro for that date. Check OpenAI’s current deprecations page before planning a migration.
When are the listed GPT-4o and GPT-4.1 API snapshots scheduled to retire?
The source lists dated snapshots of GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini for Jan. 14, 2027, with GPT-6 Luna named as their replacement. It says the plain-name model pages are also marked deprecated.
Are the replacements guaranteed to cost less?
No. The source’s Nov. 1 price comparison shows lower listed prices for some moves, such as GPT-4o to GPT-6 Luna, but higher prices for others, including GPT-5 nano to GPT-5.6 Luna. Prices can change, and actual spending depends on usage.
Will a replacement model behave exactly like the model it replaces?
The source does not establish that. It warns that reasoning models may affect token billing, parameter compatibility and output behavior. Applications should test representative requests and explicitly specify required response formats before migration.
What should API users do first?
Search code and workflow tools for affected model IDs, check the latest OpenAI deprecation and pricing pages, then test the listed replacement with realistic requests. Teams with contractual commitments can ask their OpenAI account team how the schedule applies to their account.
Source: ThorstenMeyerAI.com
