🔍 Read the full analysis: Moving Beyond GPT-4o, GPT-4.1, And GPT-5-nano In OpenAI’s API on ThorstenMeyerAI.com
Get smart everyday buys 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 API deprecation schedule says several older models have already been shut down, with GPT-5 models scheduled to leave on Dec. 11, 2026, and GPT-4o and GPT-4.1 snapshots on Jan. 14, 2027. The replacements listed in the source are reasoning models with different pricing and request behavior, so developers need to check model IDs, update integrations and test outputs before switching.
OpenAI’s API deprecation schedule lists shutdowns for GPT-5 models on Dec. 11, 2026, and GPT-4o and GPT-4.1 snapshots on Jan. 14, 2027, requiring developers to review applications that call those model IDs. Some older models were already shut down on Oct. 23, according to the schedule reviewed by ThorstenMeyerAI.com on Nov. 1.
For the December date, the listed models include gpt-5, gpt-5-mini and gpt-5-nano, as well as gpt-5-pro, o3 and o3-pro. The source says OpenAI lists gpt-5.6-sol, gpt-5.6-terra and gpt-5.6-luna as replacements for different models in this group. Fine-tuned versions are also scheduled to go when their base models shut down; the article says the listed replacements do not support fine-tuning.
On Jan. 14, the schedule covers dated snapshots of GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini. The recommended replacement given for those entries is gpt-6-luna. The article cautions that the schedule names dated snapshots while developers may use shorter model names; it advises checking those names and related integrations rather than assuming an application is unaffected.
The source also reports that several models, including gpt-3.5-turbo, gpt-4-turbo, gpt-4.1-nano, o1 and o4-mini, were shut down on Oct. 23. It says OpenAI’s Evals platform, Agent Builder and reusable prompt objects are scheduled to shut down on Nov. 30, with existing evaluations already read-only as of Oct. 31. These dates and details are reported from the OpenAI pages cited by ThorstenMeyerAI.com, not independently verified here.
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 change matters to teams whose products, internal tools or automated workflows call the affected API models. Once a model is switched off, a request that still names it may fail; changing the model ID alone may not preserve the same output, response time, cost or formatting. The migration can affect customer-facing services as well as less visible scripts and no-code workflows.
The article’s pricing comparison, based on standard short-context prices per million tokens checked on Nov. 1, describes a mixed picture. It reports GPT-4o at $2.50 per million input tokens and $10 per million output tokens, compared with $0.10 and $0.50 for gpt-6-luna. But it says the listed moves from GPT-5 nano to GPT-5.6 luna raise the input price from $0.05 to $0.20 and output from $0.40 to $1.20. GPT-5 mini to GPT-5.6 terra is reported as rising from $0.25 to $2 for input and $2 to $12 for output. These are source-reported prices, not a forecast of any customer’s total bill; token use and current pricing should be checked directly.
Behavior is another migration concern. The article describes the listed replacements as reasoning models, for which hidden reasoning tokens are billed as output. It also warns that some sampling parameters may need to be removed and that a restrictive output-token limit could leave a request with an empty answer while still incurring a charge. Developers should test representative inputs, output formats and limits before routing production traffic to a replacement.
Products Worth Considering
Dell XPS 13 9350 Copilot+ Laptop, 13.4-inch 120Hz Display, Intel Core Ultra 7 256V, 16GB RAM, 512GB SSD, Ubuntu Linux 24.04 LTS
Samsung 34-Inch ViewFinity S50GC Ultra-WQHD Monitor
Samsung Essential S3 27-Inch Curved FHD Monitor
As an affiliate, we earn on qualifying purchases.
The API Schedule and Model Spec
The development concerns the OpenAI API, not a new announcement about ChatGPT access. ThorstenMeyerAI.com says ChatGPT had already removed GPT-4o, GPT-4.1 and GPT-4.1 mini on Feb. 13, 2026. The API dates affect software and services built by developers using those model IDs, which are a separate migration problem from changes to the ChatGPT product.
The article places the deprecation schedule alongside a separate change: a revised Model Spec dated Oct. 29. It says the document removes much of its detailed style guidance, including a default to format answers in Markdown, and instructs models to interpret the intent of instructions. For applications that need a specific structure or style, the practical advice is to state that requirement in the request and test that the model follows it.
ThorstenMeyerAI.com says the schedule was checked on Nov. 1 and that OpenAI documents deprecations and emails affected customers. It also reports the schedule’s statement that generally available models receive at least six months’ notice unless safety or compliance concerns require a faster timeline. The article notes that the October notice for the January shutdown is shorter, but says the relevant schedule entry does not explain which notice rule applies.
Open Questions for Developers
The schedule reviewed by ThorstenMeyerAI.com does not explain why the listed GPT-4o and GPT-4.1 shutdowns follow a notice period shorter than the reported six-month standard for generally available models. It is also not clear from the source whether a particular customer’s contract, committed spend or service arrangement changes its options. The article says some customers may be able to buy dedicated capacity to retain access after a shutdown, but does not specify eligibility or terms.
Replacement prices and behavior can change, and the comparisons are a snapshot of standard short-context rates reported on Nov. 1, not a full estimate for every workload. The source also does not provide independent test results showing that the replacements will match each retired model’s performance on a given application. Teams should confirm current model availability, pricing and migration terms with OpenAI and test their own use cases.
Dates to Check Before Migration
Teams should first search code, configuration files, test fixtures, workflow builders and monitoring systems for the affected model IDs, including dated snapshots. The source-reported near-term dates are Nov. 30 for Evals, Agent Builder and reusable prompts, Dec. 11 for the listed GPT-5 and o3 models, and Jan. 14 for the GPT-4o and GPT-4.1 snapshots. Later dates in 2027 affect additional audio, transcription and other model families, according to the article.
Before changing production traffic, developers can run evaluation sets against the proposed replacement, check structured-output and formatting requirements, review sampling parameters and set output limits that leave room for the new model’s behavior. They can also compare token use and current prices against their own traffic patterns. The article says OpenAI emails affected customers and documents the schedule; customers with contracts or committed spend can ask their account team about notice periods and continued-access options.
The schedule reviewed on Nov. 1 is a point-in-time account. The next step is to verify each model’s current status and replacement in OpenAI’s live documentation, then monitor for any revised dates or instructions before the relevant shutdown.
Key Questions
When are GPT-5 models scheduled to leave the API?
The source article says OpenAI’s schedule sets Dec. 11, 2026 for gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro, o3 and o3-pro. Check the current deprecation page for any changes.
When are GPT-4o and GPT-4.1 API snapshots scheduled to shut down?
The article reports a shutdown date of Jan. 14, 2027 for listed 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.
Will changing the model ID be enough?
Not necessarily. The source describes differences in reasoning behavior, billing, supported request parameters and output formatting. Developers should test their application’s actual prompts and response requirements before deployment.
Will the replacement models cost less?
It depends on the model being replaced. The source’s Nov. 1 short-context price comparison reports lower listed rates for some GPT-4o-family migrations and higher rates for the listed GPT-5 nano and GPT-5 mini migrations. Prices and total costs should be checked against current documentation and actual token use.
Source: ThorstenMeyerAI.com
