🔍 Read the full analysis: OpenAI’s GPT-4o, GPT-4.1, And GPT-5-nano API Exit: A Migration Checklist on ThorstenMeyerAI.com
Get hardware and tech essentials 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 deprecation schedule lists API shutdowns on December 11, 2026, and January 14, 2027, affecting GPT-5 models and GPT-4o and GPT-4.1 snapshots. The source lists newer models as replacements, but flags changes in price, reasoning behavior and formatting expectations that developers should test before switching.
OpenAI’s API deprecation schedule sets December 11, 2026, for the removal of GPT-5, GPT-5 mini and GPT-5-nano, followed by GPT-4o and GPT-4.1 model snapshots on January 14, 2027, according to a November 1 report by Thorsten Meyer. The changes affect applications and services using those API model IDs, and developers may need to update integrations and test replacements before the deadlines.
The report says GPT-5, GPT-5 mini, GPT-5-nano, GPT-5-pro, o3 and o3-pro are scheduled to leave the API on December 11. The listed replacements include 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. The report says GPT-5-pro and o3-pro are mapped to GPT-5.6-sol with its pro reasoning mode.
On January 14, 2027, the schedule covers dated snapshots of GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini. The report identifies GPT-6-luna as the recommended replacement for those entries. It also says several other model IDs, including GPT-4.1-nano, the original GPT-4o snapshot, GPT-4-turbo, GPT-3.5-turbo, o1 and o4-mini, were scheduled to stop working on October 23, 2026. Calls that still use those IDs may already fail.
The report distinguishes the API changes from ChatGPT: it says GPT-4o, GPT-4.1 and GPT-4.1 mini were removed from ChatGPT on February 13, 2026. It also says OpenAI’s notice covers fine-tuned models based on retiring models, while the listed replacements do not support fine-tuning. Developers should verify the applicable model entry and account-specific notice with OpenAI before changing production systems.
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 Production Apps
A retired model ID can break an application even if its surrounding code has not changed. Hard-coded model names may live in configuration files, tests, scheduled jobs or no-code tools, so migration requires more than updating a single visible setting. Teams need to find every use, change it and confirm that the replacement performs the required work.
The listed replacements may also alter operating costs. Meyer’s report compares standard short-context prices per million tokens, based on OpenAI’s pricing page as checked on November 1. It reports that GPT-4o is listed at $2.50 per million input tokens, compared with $0.10 for GPT-6-luna. In contrast, GPT-5-nano’s listed replacement, GPT-5.6-luna, is reported at four times the input price and three times the output price. These figures are specific to the models and pricing conditions cited; teams should recheck current prices and estimate costs using their own workloads.
Behavior may change as well as price. The report describes the replacements as reasoning models, with reasoning tokens billed as output. It warns that some sampling parameters may not be supported and that a restrictive output-token limit could result in an empty answer that still incurs a charge. Those are reasons to test task completion, latency, token use and failure handling rather than treating a successful API response as proof of an equivalent migration.
Products Worth Considering
LG UltraGear 27G640A-B 27-Inch QHD IPS Gaming Monitor, 300Hz, 1ms, G-SYNC Compatible, FreeSync Premium, DisplayHDR 400
LG UltraGear 45GX900A-B 45-Inch Curved OLED Gaming Monitor
Logitech MX Keypad Programmable Macro Pad, Graphite
As an affiliate, we earn on qualifying purchases.
Published Shutdown Timeline
Meyer says the dates and model mappings were taken from OpenAI’s deprecations page, which the report checked on November 1, 2026. According to the report, OpenAI says it emails affected customers and documents deprecations on that page. The already-passed October 23 date makes the schedule relevant to developers who have not checked older integrations as well as those planning for December and January.
The report also flags a separate deadline: OpenAI’s Evals platform, Agent Builder and reusable prompt objects are scheduled to shut down on November 30, 2026. Existing evals became read-only on October 31, it says. That matters to migration planning because teams relying on those tools may need to preserve or replace their testing workflows before the end of November.
A revised Model Spec dated October 29 is another reported change. Meyer says it removes much of the detailed style guidance, including a default for Markdown formatting, and instructs models to follow the intent of instructions. The article quotes OpenAI as saying its models “do not yet fully reflect” the Spec. For developers, the practical takeaway is to specify required output formats directly and test whether applications can handle variations.
Pricing and Notice Questions
Some details in the schedule require confirmation by affected customers. Meyer notes that the report’s October 14 notice for the January 14 shutdown gives three months’ notice, while the deprecations page is described as promising at least six months for generally available models unless safety or compliance concerns call for a faster timeline. The report says the entry does not explain which rule applies. Customers with contracts or committed spend may want to ask their OpenAI account team how the dates apply to them.
The source provides selected price comparisons, not a complete cost forecast for every migration. Actual spending depends on usage, input and output volume, caching, context length and current pricing. The report also does not establish that replacement models will match the old models’ output quality or response behavior for any particular application. Migration results, customer-specific exceptions and the precise availability of dedicated capacity remain unclear from the supplied material.
Audit, Test and Confirm Dates
Developers should first inventory model IDs across source code, configuration, test fixtures, automation tools and deployed services. The report recommends treating the short GPT-4o and GPT-4.1 names as affected alongside the dated snapshots because the corresponding model pages are marked deprecated and the snapshots appear on the January list. Teams should separately check for IDs that were scheduled to stop working on October 23.
Before switching production traffic, run representative tasks against the listed replacement and compare results with the current model. Check structured output and formatting, unsupported parameters, reasoning-token use, response limits, empty-answer handling, latency and estimated cost. Preserve existing evaluation material where needed, given the reported November 30 shutdown of Evals and related tools. Finally, check OpenAI’s live deprecations and pricing pages and confirm account-specific arrangements; the next scheduled model shutdowns in the source are December 11 and January 14.
Key Questions
When are GPT-5-nano and the other GPT-5 models scheduled to leave the API?
The report says GPT-5, GPT-5 mini, GPT-5-nano, GPT-5-pro, o3 and o3-pro are scheduled for shutdown on December 11, 2026.
When are GPT-4o and GPT-4.1 API snapshots scheduled to shut down?
The listed GPT-4o, GPT-4o mini, GPT-4.1 and GPT-4.1 mini snapshots are scheduled for January 14, 2027, according to the report.
Which replacement does the report list for GPT-4o?
It identifies GPT-6-luna as the recommended replacement for the listed GPT-4o and GPT-4.1 snapshots. Developers should verify the current mapping with OpenAI before deployment.
Could moving to a replacement change API costs?
Yes. The price comparisons in the report vary by model: some listed replacements cost less per token, while GPT-5-nano’s listed replacement has higher input and output prices. Prices and total costs depend on current rates and actual usage.
What should developers test before migrating?
Test application-specific output quality, required formatting, parameter support, token limits, reasoning-token charges, latency and error handling. Also search for model IDs across code, configuration and automation tools.
Source: ThorstenMeyerAI.com
