SunsetDiff

Azure OpenAI GPT-4.1 and GPT-4o retirement on April 14, 2027

The dataset has 6 Azure OpenAI ids with shutdown date 2027-04-14: gpt-4.1-2025-04-14, gpt-4.1-mini-2025-04-14, gpt-4.1-nano-2025-04-14, gpt-4o-2024-08-06, gpt-4o-2024-11-20, gpt-4o-mini-2024-07-18. The retirement schedule lists that date on each of those rows. The replacement cell is gpt-5.1 for gpt-4o-2024-08-06, gpt-4o-2024-11-20. The replacement cell is empty for gpt-4.1-2025-04-14, gpt-4.1-mini-2025-04-14, gpt-4.1-nano-2025-04-14, gpt-4o-mini-2024-07-18, so those cells say Not published. The lifecycle page says a Retired model is removed from service and all inference requests return 410 Gone. The same schedule lists Azure gpt-5.1 version 2025-11-13 as GA with retirement date 2027-07-13. It does not print 2027-04-01 as an Azure gpt-5.1 shutdown.

Last reviewed . Publisher: SunsetDiff.

Steps

  1. Find deployments. Call Deployments List, or Get-AzCognitiveServicesAccountDeployment, for each Azure OpenAI resource. Read properties.model.name and properties.model.version. A deployment name can differ from the model name. gpt-4.1 version 2025-04-14 is the dataset id gpt-4.1-2025-04-14. gpt-4.1-mini version 2025-04-14 is gpt-4.1-mini-2025-04-14. gpt-4.1-nano version 2025-04-14 is gpt-4.1-nano-2025-04-14. gpt-4o version 2024-08-06 is gpt-4o-2024-08-06. gpt-4o version 2024-11-20 is gpt-4o-2024-11-20. gpt-4o-mini version 2024-07-18 is gpt-4o-mini-2024-07-18.
  2. Pick a replacement. The schedule names gpt-5.1 for gpt-4o 2024-08-06 and gpt-4o 2024-11-20. The replacement cell is empty for gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, and gpt-4o-mini, so shortlist a model yourself for those four. Before you deploy gpt-5.1, read the Azure schedule row for version 2025-11-13. That row is GA and its retirement date is 2027-07-13. Microsoft's Azure pages do not print 2027-04-01 as a gpt-5.1 shutdown.
  3. Test. Send one real request to the model you picked, using a prompt you send now. Do that before April 14, 2027. Check the reply, the tools, and the fields the new model rejects.
  4. Redeploy before the date. Create a deployment of the model you tested and move traffic before April 14, 2027. Where the schedule names a replacement, that cell is the automatic-upgrade target where an upgrade is supported. Provisioned deployments are not auto-upgraded. A deployment set to NoAutoUpgrade stops working on the retirement date.

Models and dates

These 6 ids are the Azure OpenAI rows whose shutdown date is 2027-04-14. The model id links to its SunsetDiff model page. Lifecycle is the schedule's Lifecycle column, copied from the source excerpt stored on the row. Shutdown date and replacement are the fields stored on the row. Not published means the replacement field is empty. These rows do not store a deprecation_date. gpt-4.1-2025-04-14 (Deprecated), gpt-4.1-mini-2025-04-14 (Deprecated), gpt-4.1-nano-2025-04-14 (Deprecated), gpt-4o-2024-08-06 (Deprecated), gpt-4o-2024-11-20 (Legacy), gpt-4o-mini-2024-07-18 (Deprecated).

The lifecycle page says: "For gpt-4o versions 2024-08-06 and 2024-11-20, gpt-4o-mini version 2024-07-18, and gpt-4.1-mini version 2025-04-14, all active customer-facing base-model inference offers in Azure public cloud retire on April 14, 2027, in all applicable regions. Already-retired Regional Standard deployments remain retired." Footnote 3 on the schedule says: "April 14, 2027 applies to all active customer-facing base-model inference offers in all applicable regions in Azure public cloud for gpt-4o versions 2024-08-06 and 2024-11-20, gpt-4o-mini version 2024-07-18, and gpt-4.1-mini version 2025-04-14. Already-retired Regional Standard deployments remain retired. For fine-tuning training and deployment retirement dates, see the separate schedules below." That sentence names gpt-4o 2024-08-06, gpt-4o 2024-11-20, gpt-4o-mini 2024-07-18, and gpt-4.1-mini 2025-04-14. The schedule still lists retirement date 2027-04-14 for gpt-4.1 2025-04-14 and gpt-4.1-nano 2025-04-14. Those two rows do not carry footnote 3.

The lifecycle page also says: "Check the Model retirement schedule for the current retirement dates and replacement model, since these details are subject to change."

6 Azure OpenAI model ids with shutdown date 2027-04-14.
Model idLifecycle on the scheduleShutdown dateRecommended replacement
gpt-4.1-2025-04-14Deprecated2027-04-14Not published
gpt-4.1-mini-2025-04-14Deprecated2027-04-14Not published
gpt-4.1-nano-2025-04-14Deprecated2027-04-14Not published
gpt-4o-2024-08-06Deprecated2027-04-14gpt-5.1
gpt-4o-2024-11-20Legacy2027-04-14gpt-5.1
gpt-4o-mini-2024-07-18Deprecated2027-04-14Not published

Sources: Azure OpenAI retirement schedule , Foundry Models lifecycle , checked November 4, 2026.

Replacements Microsoft names

The schedule says: "The Replacement column identifies Microsoft's recommended replacement and, where supported, the target for automatic upgrades at retirement." It also says: "You don't need to wait for a replacement to be listed before evaluating or manually migrating to another compatible model." The lifecycle page says: "The replacement listed in the Model retirement schedule is Microsoft's recommended migration target and, where supported, the model used for automatic upgrades at retirement. It doesn't limit your manual migration choices."

The replacement cell is gpt-5.1 on gpt-4o-2024-08-06, gpt-4o-2024-11-20. The cell prints gpt-5.1 with no version in parentheses. The recommended replacement is the official replacement stored on each row. gpt-4o-2024-08-06: gpt-5.1. gpt-4o-2024-11-20: gpt-5.1.

The replacement cell is empty on gpt-4.1-2025-04-14, gpt-4.1-mini-2025-04-14, gpt-4.1-nano-2025-04-14, gpt-4o-mini-2024-07-18. Empty means Microsoft did not name a recommended replacement on that row. This guide does not add one.

gpt-4o version 2024-05-13 is a different row. It retires on 2027-01-14. The schedule cell on that row is gpt-5.1 (2025-11-13). The lifecycle page says: "All active customer-facing base-model inference offers for gpt-4o version 2024-05-13 in Azure public cloud retire on January 14, 2027, in all applicable regions." Then: "The replacement model is gpt-5.1 version 2025-11-13." Those two sentences are about version 2024-05-13. They are not the April 14 rows. See gpt-4o-2024-05-13, Azure OpenAI shutdowns on January 14, 2027, and Azure OpenAI retirements from January 12 to February 9, 2027.

Sources: Azure OpenAI retirement schedule , Foundry Models lifecycle , checked November 4, 2026.

OpenAI's April 1 date and Azure gpt-5.1

OpenAI's API deprecations page says: "The following models are deprecated and will be removed from the API on April 1, 2027, with six months' notice. Migrate to the recommended replacements before the shutdown date." That date is 2027-04-01. The OpenAI rows are on GPT-5.1, gpt-5.3-codex, and gpt-5.4-nano shutdown on April 1, 2027.

Microsoft's retirement schedule and lifecycle page do not print 2027-04-01 as a shutdown date for gpt-5.1. The schedule has its own Azure row: gpt-5.1 version 2025-11-13, lifecycle GA, retirement date 2027-07-13, replacement cell empty. SunsetDiff stores that row as gpt-5.1-2025-11-13. That 2027-07-13 date is the retirement date the schedule prints for Azure gpt-5.1 version 2025-11-13. gpt-5-mini version 2025-08-07 and gpt-5.2-codex version 2026-01-14 use that same Azure date. See Azure OpenAI gpt-5.1, gpt-5-mini, and gpt-5.2-codex retirement on July 13, 2027.

The replacement stored on the two gpt-4o rows is the Azure id gpt-5.1. The shutdown date stored on that id is Not published. The schedule does not print an undated gpt-5.1 row. It prints version 2025-11-13.

The string 2027-04-01 does appear on the Azure fine-tune tables. It is "No earlier than 2027-04-01" for gpt-4o version 2024-08-06 and gpt-4o-mini version 2024-07-18. That is a training floor for those fine-tunes. It is not a gpt-5.1 shutdown, and it is not the OpenAI API date applied to Azure.

Sources: Azure OpenAI retirement schedule , Foundry Models lifecycle , OpenAI deprecations , checked November 4, 2026.

Fine-tuned training and deployment

The schedule and the lifecycle page both say: "Fine-tuned models retire in two phases: training and deployment." And: "Unless explicitly stated, training retires no earlier than the base model retirement date." Both pages say: "For existing customers only. Otherwise, training retirement occurs at base model retirement."

The fine-tune dates stored on these rows match both tables. gpt-4.1-2025-04-14: training retirement No earlier than 2027-04-14. Fine-tuned deployment retirement 2027-10-14. gpt-4.1-mini-2025-04-14: training retirement No earlier than 2027-04-14. Fine-tuned deployment retirement 2027-10-14. gpt-4.1-nano-2025-04-14: training retirement No earlier than 2027-04-14. Fine-tuned deployment retirement 2027-10-14. gpt-4o-2024-08-06: training retirement No earlier than 2027-04-01. Fine-tuned deployment retirement 2027-10-01. gpt-4o-2024-11-20: no fine-tune dates are stored, and the fine-tune tables do not list this version. gpt-4o-mini-2024-07-18: training retirement No earlier than 2027-04-01. Fine-tuned deployment retirement 2027-10-01.

gpt-4o version 2024-11-20 is not in either fine-tune table. A base deployment of that version still uses the retirement date in the first table.

A fine-tuned deployment retirement is later than the base retirement date on the rows that list one. Do not treat the fine-tune deployment date as the date a base deployment stops.

Sources: Azure OpenAI retirement schedule , Foundry Models lifecycle , checked November 4, 2026.

What happens to a deployment on the date

The lifecycle table says Retired means: "Removed from service. All inference requests return 410 Gone." New deployments are not allowed, and existing deployments do not work. The same page says the API value lifecycleStatus Deprecated means the model is retired and inference returns 410 Gone. The docs stage Deprecated is lifecycleStatus Deprecating, and inference still works. The sentences and the status map are on Azure OpenAI retired models return 410 Gone.

The lifecycle page says: "For Global Standard, Data Zone Standard, and Standard deployment types, Microsoft manages automatic upgrades when a model version is retired:" It also says: "Provisioned deployments are NOT auto-upgraded. Provisioned customers must manually migrate to the replacement model." The migration page says: "Standard, Global Standard, and Data Zone Standard (pay-as-you-go) deployments are auto-upgraded on a rolling, region-by-region schedule." And: "Provisioned (PTU) deployments are not auto-upgraded." And: "Batch deployments follow the side-by-side path: deploy the new model, resubmit jobs, retire the old deployment."

Working with models says: "Automatic model updates are only supported for Standard deployment types." OnceCurrentVersionExpired means: "Once the retirement date is reached the model deployment automatically upgrades to the current default version." NoAutoUpgrade means: "The model deployment never automatically upgrades. Once the retirement date is reached the model deployment stops working." And: "null is equivalent to OnceCurrentVersionExpired."

The same page says: "When you select a specific model version for a deployment, this version remains selected until you either choose to manually update yourself, or once you reach the retirement date for the model." Then: "When the retirement date is reached the model will automatically upgrade to the default version at the time of retirement." A deployment you pinned to one of these versions can still move on the retirement date unless versionUpgradeOption is NoAutoUpgrade. NoAutoUpgrade does not move, and the deployment stops. The replacement cell is the target where an automatic upgrade is supported. The four rows with an empty cell do not name that target.

Sources: Azure OpenAI retirement schedule , Foundry Models lifecycle , Working with Azure OpenAI models , Model migration process , checked November 4, 2026.

Find deployments that use these versions

The migration page says: "You also need an inventory of the model deployments your workload uses, including their deployment types (Standard, Provisioned, or Batch)." Working with models says: "To query the current model deployment settings including the deployment upgrade configuration for a given resource use Deployments List." If the value is null, you won't see a versionUpgradeOption property. The model versions page says: "Go to your deployment in the Foundry portal, then open the Details tab to see the current model version." And: "Query the deployments endpoint for your resource. The response includes the model version for each deployment."

The example response puts the model name and version on properties.model. The deployment's own name is the name field next to that object. Match properties.model.name and properties.model.version to the ids in the table. gpt-4o version 2024-11-20 is the dataset id gpt-4o-2024-11-20.

Also search the repository. A hit is a candidate, not proof a deployment still uses that version. How to find every model ID in your codebase covers SDK argument names. The scan page builds a search from dataset ids that have a shutdown date.

Azure PowerShell, list deployments for one account

Get-AzCognitiveServicesAccountDeployment -ResourceGroupName {ResourceGroupName} -AccountName {AccountName}

Deployments List

GET https://management.azure.com/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.CognitiveServices/accounts/{accountName}/deployments?api-version=2023-05-01

ripgrep

rg -n -w -e 'gpt-4.1-2025-04-14' -e 'gpt-4.1-mini-2025-04-14' -e 'gpt-4.1-nano-2025-04-14' -e 'gpt-4o-2024-08-06' -e 'gpt-4o-2024-11-20' -e 'gpt-4o-mini-2024-07-18'

Sources: Working with Azure OpenAI models , Model versions , Model migration process , checked November 4, 2026.

Redeploy before April 14, 2027

Create a deployment of a model you have tested, point traffic at it, and confirm one real request before April 14, 2027. Do that for each of the 6 versions in the table.

Working with models describes two ways to change a provisioned deployment once you have chosen a target. In-place migration keeps the deployment name and moves traffic. Multi-deployment migration creates a second deployment, shifts traffic, then deletes the old one.

The batch of these rows is Azure OpenAI shutdowns on April 14, 2027. The Azure OpenAI provider page lists the other stored rows. Earlier Azure dates are on Azure OpenAI retirements from November 15 to December 16, 2026.

The pre-migration test checklist is the longer list: evals, rejected fields, token limits, tools, price, and latency. These Azure rows do not store a price.

Sources: Model migration process , Working with Azure OpenAI models , Azure OpenAI retirement schedule , checked November 4, 2026.

Related SunsetDiff pages

All guides

Questions

Which Azure OpenAI versions retire on April 14, 2027?

The dataset lists gpt-4.1-2025-04-14, gpt-4.1-mini-2025-04-14, gpt-4.1-nano-2025-04-14, gpt-4o-2024-08-06, gpt-4o-2024-11-20, gpt-4o-mini-2024-07-18. The retirement schedule lists shutdown date 2027-04-14 for each of them. gpt-4.1-2025-04-14 (Deprecated), gpt-4.1-mini-2025-04-14 (Deprecated), gpt-4.1-nano-2025-04-14 (Deprecated), gpt-4o-2024-08-06 (Deprecated), gpt-4o-2024-11-20 (Legacy), gpt-4o-mini-2024-07-18 (Deprecated).

What is the official replacement?

The recommended replacement is the official replacement stored on each row. gpt-4.1-2025-04-14: Not published. gpt-4.1-mini-2025-04-14: Not published. gpt-4.1-nano-2025-04-14: Not published. gpt-4o-2024-08-06: gpt-5.1. gpt-4o-2024-11-20: gpt-5.1. gpt-4o-mini-2024-07-18: Not published. The schedule says: "The Replacement column identifies Microsoft's recommended replacement and, where supported, the target for automatic upgrades at retirement." The cell is empty on gpt-4.1-2025-04-14, gpt-4.1-mini-2025-04-14, gpt-4.1-nano-2025-04-14, gpt-4o-mini-2024-07-18.

Does OpenAI's April 1, 2027 shutdown of gpt-5.1 apply to Azure?

Microsoft's retirement schedule and lifecycle page do not print 2027-04-01 as an Azure gpt-5.1 shutdown. The schedule lists Azure gpt-5.1 version 2025-11-13 as GA with retirement date 2027-07-13 and an empty replacement cell. OpenAI's deprecations page says: "The following models are deprecated and will be removed from the API on April 1, 2027, with six months' notice. Migrate to the recommended replacements before the shutdown date." That sentence is the OpenAI API. See GPT-5.1, gpt-5.3-codex, and gpt-5.4-nano shutdown on April 1, 2027. The Azure id gpt-5.1 stores shutdown date Not published.

What does Azure return after retirement?

The lifecycle page says a Retired model is removed from service and: "Removed from service. All inference requests return 410 Gone." See Azure OpenAI retired models return 410 Gone.

Will every deployment upgrade itself?

No. The lifecycle page says: "For Global Standard, Data Zone Standard, and Standard deployment types, Microsoft manages automatic upgrades when a model version is retired:" And: "Provisioned deployments are NOT auto-upgraded. Provisioned customers must manually migrate to the replacement model." Working with models says: "Automatic model updates are only supported for Standard deployment types." NoAutoUpgrade means: "The model deployment never automatically upgrades. Once the retirement date is reached the model deployment stops working." null is equivalent to OnceCurrentVersionExpired. The four rows with an empty replacement cell do not name an upgrade target.

How do I find deployments that still use these versions?

Working with models says: "To query the current model deployment settings including the deployment upgrade configuration for a given resource use Deployments List." Read properties.model.name and properties.model.version. The model versions page says: "Go to your deployment in the Foundry portal, then open the Details tab to see the current model version." The migration page says: "You also need an inventory of the model deployments your workload uses, including their deployment types (Standard, Provisioned, or Batch)."

Do fine-tuned deployments retire on April 14, 2027?

The base retirement date is 2027-04-14. The fine-tune tables use a later deployment date on the rows that list one. gpt-4.1-2025-04-14: training retirement No earlier than 2027-04-14. Fine-tuned deployment retirement 2027-10-14. gpt-4.1-mini-2025-04-14: training retirement No earlier than 2027-04-14. Fine-tuned deployment retirement 2027-10-14. gpt-4.1-nano-2025-04-14: training retirement No earlier than 2027-04-14. Fine-tuned deployment retirement 2027-10-14. gpt-4o-2024-08-06: training retirement No earlier than 2027-04-01. Fine-tuned deployment retirement 2027-10-01. gpt-4o-2024-11-20: no fine-tune dates are stored, and the fine-tune tables do not list this version. gpt-4o-mini-2024-07-18: training retirement No earlier than 2027-04-01. Fine-tuned deployment retirement 2027-10-01. Both pages say: "For existing customers only. Otherwise, training retirement occurs at base model retirement." gpt-4o version 2024-11-20 is not in the fine-tune tables.

More guides

Deprecation alerts

We email you before models shut down. Unsubscribe anytime.

Deprecation alert signup
Providers (optional)