🔍 Read the full analysis: How To Prepare For OpenAI Turning Off 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 published deprecation schedule, as reported by ThorstenMeyerAI.com on Nov. 1, 2026, lists API shutdowns on Dec. 11, 2026, and Jan. 14, 2027, alongside model IDs that stopped working Oct. 23. Developers should inventory model IDs, check the proposed replacements and test behavior, pricing and output limits before switching; some schedule and pricing details need confirmation with OpenAI.
OpenAI’s API deprecation schedule lists model retirements on Dec. 11, 2026, and Jan. 14, 2027, with several other model IDs reported as already shut down on Oct. 23. The changes affect developers and organizations whose applications call those models directly; they will need to check their configurations and test replacement models before the relevant dates.
According to ThorstenMeyerAI.com, which says it checked OpenAI’s deprecations page on Nov. 1, the Dec. 11 retirement list includes GPT-5, GPT-5 mini, GPT-5-nano, GPT-5-pro, o3 and o3-pro. The report says OpenAI recommends GPT-5.6 variants as replacements: GPT-5.6-sol 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 directed to GPT-5.6-sol with its pro reasoning mode.
The next listed date is Jan. 14, 2027. The source names dated snapshots for GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini, and says OpenAI recommends GPT-6-luna for those models. It also reports that short model names such as gpt-4o and gpt-4.1 are marked deprecated on their model pages, so teams should not assume that using a short alias avoids the scheduled change.
The report says model IDs including gpt-4.1-nano, gpt-4o-2024-05-13, gpt-4-turbo, gpt-3.5-turbo, o1 and o4-mini were shut down on Oct. 23. Calls using affected IDs may fail. It also says fine-tuned versions are scheduled to follow their base models, while the listed replacement models do not support fine-tuning. Developers with customized models should verify their options with OpenAI rather than assuming a direct migration is available.
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 dates matter because model IDs are often stored in application code, configuration files, test fixtures or automation tools that may not receive regular review. A service can continue operating until it makes a request to a retired model; then that specific call may fail. Finding every model reference is therefore a practical first step, including references outside the main application.
Changing the model may also change the application’s cost and behavior. The source’s price comparison, based on OpenAI’s listed standard prices for prompts up to 272,000 tokens as checked Nov. 1, describes sharply different results by model. It reports GPT-6-luna at $0.10 per million input tokens compared with $2.50 for GPT-4o, but GPT-5.6-luna at $0.20 compared with $0.05 for GPT-5-nano. These are source-reported rates, not a forecast of an individual customer’s bill; usage, output volume, caching and later price changes affect costs.
Behavior is another migration risk. The article characterizes the proposed replacements as reasoning models and warns that reasoning tokens are billed as output. It says some sampling parameters must be removed and that restrictive output limits can result in an empty, billed response. Teams should test representative requests and monitor both response quality and billing before moving production traffic.
Products Worth Considering

Apple Mac mini with M2 chip, 16GB unified memory, 256GB SSD, Silver

Dell XPS Tower 8960 Desktop, Intel Core i7-13700, NVIDIA GeForce RTX 4060, 16GB DDR5, 512GB SSD

Dell XPS 13 13.4-Inch Touchscreen Laptop, Intel Core 5 320, 16GB RAM, 512GB SSD
As an affiliate, we earn on qualifying purchases.
OpenAI’s Published Retirement Schedule
The source says OpenAI’s deprecations page documents each retirement and that affected customers are emailed. It reports that OpenAI’s ChatGPT product removed GPT-4o, GPT-4.1 and GPT-4.1 mini on Feb. 13, 2026, while the dates in this report concern the API used by apps and bots. The two changes affect different ways of accessing OpenAI models.
There are related service changes before the December model retirements. ThorstenMeyerAI.com says OpenAI plans to shut down its Evals platform, Agent Builder and reusable prompt objects on Nov. 30, 2026, and that existing evals became read-only on Oct. 31. The report also describes a Model Spec revision dated Oct. 29, 2026, which it says removes much of the prior style guidance, including a default preference for Markdown. These details make it sensible to review not only model names but also evaluation and formatting dependencies.
The source lists further retirements in 2027, including text-to-speech models on Jan. 6, older audio and realtime models on Jan. 20, transcription models on Feb. 26, and GPT-5.1, GPT-5.4-nano and GPT-5.3-codex on Apr. 1. These dates and mappings are reported from the schedule as it stood on Nov. 1, 2026; developers should consult the live OpenAI documentation before acting.
Schedule and Migration Questions
The report does not establish whether OpenAI has revised any dates or model mappings since its Nov. 1 check. It says the notice for the Jan. 14 retirements was issued on Oct. 14, three months ahead, while OpenAI’s page promises at least six months’ notice for generally available models unless safety or compliance concerns require a faster timeline. Why the shorter interval applies is not stated in the material; customers with contracts or committed spend are advised by the source to ask their OpenAI account team.
It is also unclear from the supplied material whether every account has access to the same replacement models, whether dedicated capacity will be available to all affected users, or how migration will work for fine-tuned deployments when the listed replacements do not support fine-tuning. The article reports that some customers may be able to buy dedicated capacity for continued access after shutdown, but gives no eligibility criteria. Replacement pricing and capabilities can change, so current documentation and account-specific terms should be checked.
Audit Before Each Retirement Date
Developers should begin with an inventory of model IDs across source code, environment settings, automated workflows and test data. Mark any IDs on the Oct. 23 list for immediate investigation, then prioritize the Dec. 11 and Jan. 14 deadlines. Confirm the applicable replacement against OpenAI’s current deprecation and model pages rather than relying only on a copied schedule.
Before switching production traffic, run the replacement against representative prompts and compare output format, accuracy for the application’s task, latency, token use and total cost. Review parameters that the source says may not be supported by reasoning models, and check output limits to reduce the risk of empty responses. Re-test fine-tuned workflows separately and ask OpenAI about continued access or migration options where needed. The next listed milestones are the Nov. 30 platform changes, followed by the Dec. 11 model retirements and the Jan. 14 GPT-4 family retirements.
Key Questions
When are GPT-5-nano and the other GPT-5 API models scheduled to be retired?
The schedule reported by ThorstenMeyerAI.com lists Dec. 11, 2026 for GPT-5, GPT-5 mini, GPT-5-nano and GPT-5-pro, as well as o3 and o3-pro. Check OpenAI’s current deprecations page for updates.
When are GPT-4o and GPT-4.1 API models scheduled to be retired?
The source lists Jan. 14, 2027 for specified GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini snapshots. It says GPT-6-luna is the recommended replacement for those entries.
Does the schedule apply to ChatGPT or to the API?
The dates discussed here concern the OpenAI API, which developers use in applications and bots. The source separately reports that GPT-4o, GPT-4.1 and GPT-4.1 mini were removed from ChatGPT on Feb. 13, 2026.
What should a developer do before switching models?
Locate every affected model ID, check the current replacement and pricing, then test typical requests for output quality, format, latency, token use and cost. Review model-specific parameters and output limits, and confirm options for fine-tuned models with OpenAI.
Are the replacement models guaranteed to cost less?
No. The source reports lower listed input prices for some mappings and higher prices for others, including a higher per-token price for GPT-5-nano’s proposed replacement. Actual costs depend on usage and current rates, which should be checked before migration.
Source: ThorstenMeyerAI.com
