🔍 Read the full analysis: GPT-4o, GPT-4.1, And GPT-5-nano In The OpenAI API: What Changes And When on ThorstenMeyerAI.com
Prime made for students and young adults
- Fast, free delivery for dorm and study essentials
- Prime Video and Amazon Music included
- Member-only deals
TL;DR
OpenAI’s API deprecation schedule lists GPT-5, GPT-5 mini and GPT-5-nano for retirement on Dec. 11, 2026, followed by GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini on Jan. 14, 2027. The listed replacement models differ in price and use reasoning, which can affect billing and application behavior; the timing and migration details should be checked against OpenAI’s current documentation.
OpenAI’s API deprecation schedule lists GPT-5, GPT-5 mini and GPT-5-nano for retirement on Dec. 11, 2026, and GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini for Jan. 14, 2027. The listed replacements are newer reasoning models, so developers may need to change model IDs and test application behavior, not just update a configuration value.
According to OpenAI’s deprecations page, the December changes include GPT-5 and GPT-5 mini moving to GPT-5.6-sol and GPT-5.6-terra, respectively, while GPT-5-nano is paired with GPT-5.6-luna. The source also lists o3, GPT-5-pro and o3-pro for that date, with replacements based on GPT-5.6-sol. The schedule was checked by ThorstenMeyerAI.com on Nov. 1, 2026.
For Jan. 14, 2027, the schedule lists dated snapshots of GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini, with GPT-6-luna named as the replacement for all four. The source says the short model names are also marked deprecated in OpenAI’s model pages, and advises developers to treat them as covered by the January date.
Some earlier model IDs were listed as 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 source also reports that OpenAI’s Evals platform, Agent Builder and reusable prompt objects are scheduled to close on Nov. 30, with existing evals read-only since Oct. 31. Those product changes may affect teams preparing migration tests.
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 Means More Than Changing IDs
The retirement dates matter to companies whose applications call these models directly: a request using a retired ID may fail, while a switch to a successor can alter output, latency and cost. Teams with model names embedded in configuration files, automated workflows or test fixtures may not find every dependency in the main application code.
Pricing comparisons in the source show that the switch can cut or raise token costs depending on the model pair. At the stated short-context rates, GPT-4o is listed at $2.50 per million input tokens and $10 per million output tokens, compared with $0.10 and $0.50 for GPT-6-luna. By contrast, GPT-5-nano is listed at $0.05 input and $0.40 output, compared with $0.20 and $1.20 for GPT-5.6-luna. These are listed rates, not an estimate of a particular customer’s total bill.
The source characterizes the replacements as reasoning models, with hidden reasoning tokens billed as output. It warns that some sampling parameters may no longer apply and that a tight output-token limit can produce an empty response that is still billed. Developers should verify those behaviors in their own workloads rather than assume an unchanged interface means unchanged results.
Products Worth Considering
Apple MacBook Air 13-inch with M5 chip, 16GB memory, 1TB SSD, and 12MP Center Stage camera (Midnight)
Apple AirPods Pro 3 Wireless Earbuds with Active Noise Cancellation
DJI Osmo Mobile 8 Gimbal with Mic Mini Transmitter, Infinity Black
As an affiliate, we earn on qualifying purchases.
The API Schedule and Its Scope
This schedule concerns OpenAI API access, which powers third-party applications and internal company tools. It is separate from ChatGPT’s consumer interface. The source says GPT-4o, GPT-4.1 and GPT-4.1 mini had already been removed from ChatGPT on Feb. 13, 2026; that earlier change does not itself establish the API retirement dates.
OpenAI’s deprecation page is the source cited for the dates and replacement mappings. The source says OpenAI notifies affected customers and documents deprecations there. It also notes that fine-tuned versions follow their base model’s shutdown schedule, while the listed successor models do not support fine-tuning. That could require teams relying on customized versions to plan for a different approach, rather than a direct model swap.
The source reports that OpenAI’s Model Spec was revised on Oct. 29, 2026, removing much of its detailed style guidance, including a prior default toward Markdown formatting. The Spec is guidance about model behavior, not a separate API shutdown notice. The practical implication described by the source is that developers who require a specific format should state it explicitly in their prompts and test the result.
Notice Period and Migration Details
The schedule’s timing raises an unresolved question. The source says the GPT-4o and GPT-4.1 notice was issued on Oct. 14 for a Jan. 14 retirement, while OpenAI’s general policy, as quoted in the source, promises at least six months’ notice for generally available models except when safety or compliance concerns require faster action. The notice itself reportedly does not explain which condition applies. Developers with contractual commitments or committed spend may need to ask OpenAI directly.
The source also says some customers may be able to purchase dedicated capacity to keep access after a shutdown, but it gives no eligibility terms, prices or availability. It does not provide a complete technical migration guide or independent performance comparisons for the successor models. Exact compatibility, output quality, latency and total cost will depend on each application’s prompts and usage.
Several figures in the source are snapshots of published prices as of Nov. 1, 2026, using short-context rates for prompts up to 272,000 tokens. Prices can change, and the supplied material ends partway through its GPT-5 mini comparison. The figures should not be treated as a full cost table or as a forecast of future billing.
Check IDs and Test Successors
Developers should compare their deployed model IDs with OpenAI’s current deprecation page, including dated snapshots and short names, then inventory references across code, integrations and scheduled jobs. The source recommends testing before the shutdowns; a practical migration should compare representative prompts, structured-output requirements, error handling, latency and token use on the listed replacement.
Teams should also review output-token limits and sampling settings, since the source warns that reasoning models may treat these differently. Re-run evaluations before Nov. 30 if they rely on OpenAI’s Evals platform, Agent Builder or reusable prompt objects. OpenAI’s documentation and customer notices are the next sources to watch for any changes to dates, model mappings, pricing or dedicated-capacity options.
Key Questions
When are GPT-4o and GPT-4.1 scheduled to leave the API?
OpenAI’s schedule, as reported by ThorstenMeyerAI.com on Nov. 1, 2026, lists Jan. 14, 2027 for GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini snapshots. The source says their listed replacement is GPT-6-luna.
When are GPT-5 and GPT-5-nano scheduled for retirement?
The schedule lists Dec. 11, 2026 for GPT-5, GPT-5 mini and GPT-5-nano. The replacements listed are GPT-5.6-sol, GPT-5.6-terra and GPT-5.6-luna, respectively.
Will changing the model ID preserve the same output and cost?
Not necessarily. The source says the replacements are reasoning models and may differ in billing, supported sampling parameters and output behavior. It also reports large price differences between some model pairs, so applications should be tested and budgets recalculated using current rates.
Do fine-tuned versions follow the same shutdown dates?
According to the source’s summary of OpenAI’s policy, fine-tuned models follow the retirement schedule of their base model. The source says the listed replacement models do not support fine-tuning, so teams using customized models should check their options with OpenAI.
What should developers do first?
Check OpenAI’s current deprecation page, search for affected model IDs across application code and integrations, and test the listed successor with representative requests. Review output limits, formatting requirements, pricing and any fine-tuning dependency before changing production traffic.
Source: ThorstenMeyerAI.com
