🔍 Read the full analysis: OpenAI’s GPT-4o, GPT-4.1, And GPT-5-nano API Transition: Dates, Costs, And Migration on ThorstenMeyerAI.com
Get business pricing on tech for your team
- Business-only prices and quantity discounts
- Tax-exempt purchasing
- Multiple users, one account, clear invoices
TL;DR
OpenAI’s API deprecation schedule lists GPT-5, GPT-5 mini, GPT-5-nano and several other models for retirement on Dec. 11, 2026, followed by specified GPT-4o and GPT-4.1 snapshots on Jan. 14, 2027. The listed replacements bring substantial price differences and reasoning-model behavior changes; the source says some older model IDs already stopped working on Oct. 23.
OpenAI plans to retire GPT-5, GPT-5 mini and GPT-5-nano from its API on Dec. 11, 2026, followed by specified GPT-4o and GPT-4.1 snapshots on Jan. 14, 2027, according to the company’s deprecation schedule as reported by ThorstenMeyerAI.com. The changes affect developers and businesses whose applications call those model IDs, and migration may alter both API costs and model behavior.
The Dec. 11 list also includes GPT-5-pro, o3 and o3-pro. The source says 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. It lists GPT-5.6-sol with pro reasoning mode for GPT-5-pro and o3-pro. On Jan. 14, the listed GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini snapshots are slated to move to GPT-6-luna.
Some IDs on the deprecation page 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 source cautions that the schedule names dated snapshots, while short model names may appear in code; the related model pages reportedly mark those short names as deprecated. Fine-tuned models are also scheduled to end with their base models, and the listed replacements do not support fine-tuning.
Prices in the source are standard rates per million tokens for prompts up to 272,000 tokens, checked Nov. 1. GPT-6-luna is listed at $0.10 per million input tokens and $0.50 per million output tokens. By comparison, GPT-4o is listed at $2.50 input and $10 output; GPT-4.1 at $2 and $8. GPT-4o mini is listed at $0.15 input and $0.60 output, and GPT-4.1 mini at $0.40 and $1.60. The GPT-5-nano replacement, GPT-5.6-luna, is listed at $0.20 input and $1.20 output, compared with $0.05 and $0.40 for GPT-5-nano. GPT-5 mini’s listed move to GPT-5.6-terra changes rates from $0.25 and $2 to $2 and $12.
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 Changes Costs and Outputs
The schedule is a practical deadline for teams to find model IDs in production code, testing systems and third-party automations, then verify that replacements work before shutdown. An unnoticed dependency on a retired ID could make API requests fail; a successful switch may still change response quality, latency, formatting or cost.
The price table shows why migration cannot be treated as a uniform saving. The listed GPT-4o and GPT-4.1 replacements cost less per token than their predecessors, while the GPT-5-nano and GPT-5 mini replacements are more expensive at the listed rates. Actual spending will depend on each application’s input and output token use, caching, prompt length and request volume. The figures are not a forecast of any individual customer’s bill.
The source also describes the replacements as reasoning models. It says hidden reasoning tokens are billed as output and warns that some sampling parameters must be removed, while a restrictive output-token limit can result in an empty response that is still billed. Those behavior and billing differences make representative testing as important as changing a model name.
Products Worth Considering
Samsung 27-inch Odyssey OLED G6 QD-OLED QHD Gaming Monitor
Samsung 27 Odyssey OLED G5 (G50SF) QHD QD-OLED Gaming Monitor
LG 34GX90SA-W 34-inch Ultragear WQHD OLED Curved Gaming Monitor
As an affiliate, we earn on qualifying purchases.
API Changes Follow ChatGPT Removal
This schedule concerns the OpenAI API, which developers use to power applications and services; it is separate from model availability inside ChatGPT. The source says OpenAI removed GPT-4o, GPT-4.1 and GPT-4.1 mini from ChatGPT on Feb. 13, 2026. That earlier product change does not itself establish the API retirement dates, which the source attributes to OpenAI’s deprecation page.
The source reports two other dates relevant to migration work: OpenAI’s Evals platform, Agent Builder and reusable prompt objects at v1/prompts are scheduled to shut down Nov. 30, 2026, with existing evals read-only from Oct. 31. It also notes that OpenAI revised its Model Spec on Oct. 29, removing much of its detailed style guidance, including a prior default for Markdown formatting. The source says the new version asks models to follow the intent of instructions and quotes OpenAI as saying models “do not yet fully reflect” the Spec. These are related operational considerations, not the same event as the API model retirements.
Notice Period and Migration Details
The schedule’s scope, account-specific arrangements and any later updates should be checked directly against OpenAI’s current deprecation page. The source says the page promises at least six months’ notice for generally available models unless safety or compliance concerns require a faster timeline. It also says the GPT-4o and GPT-4.1 notice ran from Oct. 14 to Jan. 14, a three-month period, and that the entry does not explain which rule applies. Developers with contracts or committed spending may need to ask their OpenAI account team about their circumstances.
The source says some customers may be able to purchase dedicated capacity for continued access after shutdown, but does not specify eligibility, availability or price. The provided material also does not give full migration guidance, performance comparisons, or a detailed account of how every replacement handles individual workloads. Pricing can change, and the listed rates are limited to the stated short-context pricing basis; teams should verify current rates and test their own usage patterns.
Test Before the December Cutoff
Teams using affected models should inventory model IDs across code, configuration files, test fixtures and automation tools, then compare that inventory with the latest OpenAI deprecation schedule. The immediate dates in the source are Nov. 30 for Evals, Agent Builder and reusable prompt objects, Dec. 11 for the listed GPT-5 and o3 models, and Jan. 14 for the specified GPT-4o and GPT-4.1 snapshots.
A migration test should compare current and replacement models on representative prompts, including expected output format, quality, latency, token use and cost. Developers should review sampling parameters and output limits for reasoning-model compatibility, and check whether fine-tuning or other features they rely on are supported by the replacement. The source recommends making explicit formatting instructions where applications depend on a consistent style, given the reported Model Spec changes. OpenAI’s deprecation page and any account-specific communications remain the cited sources for deadline updates.
Key Questions
When are the named API models scheduled to retire?
According to the schedule described by ThorstenMeyerAI.com, GPT-5, GPT-5 mini, GPT-5-nano, GPT-5-pro, o3 and o3-pro are listed for Dec. 11, 2026. Specified GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini snapshots are listed for Jan. 14, 2027.
Which models are listed as replacements?
The source says GPT-5 and o3 are mapped to GPT-5.6-sol, GPT-5 mini to GPT-5.6-terra, and GPT-5-nano to GPT-5.6-luna. It lists GPT-6-luna for the named GPT-4o and GPT-4.1 snapshots. Check OpenAI’s current schedule for the applicable model IDs and any updates.
Will moving to a replacement always reduce API costs?
No. The rates cited in the source show lower per-token prices for GPT-6-luna than for GPT-4o and GPT-4.1, but higher listed prices for the GPT-5-nano and GPT-5 mini replacements. Actual bills depend on token use, caching and current pricing.
What should developers test before switching?
Test representative prompts for output quality, formatting, latency, token consumption and cost. Also check sampling parameters, output limits and feature support, including fine-tuning, because the source describes the replacements as reasoning models and says the listed replacements do not support fine-tuning.
Source: ThorstenMeyerAI.com
