Azure OpenAI o-series retirement on November 19, 2026
The dataset has 7 Azure OpenAI ids with shutdown date 2026-11-19: o1-2024-12-17, o1-pro-2025-03-19, o3-2025-04-16, o3-deep-research-2025-06-26, o3-mini-2025-01-31, o3-pro-2025-06-10, o4-mini-2025-04-16. The retirement schedule lists each as Deprecated, retirement date 2026-11-19. The replacement column is the official replacement stored on each row. The lifecycle page says a Retired model is removed from service and all inference requests return 410 Gone. Standard deployments can auto-upgrade. A deployment set to NoAutoUpgrade stops working. Provisioned deployments are not auto-upgraded. codex-mini-2025-05-16 is stored with shutdown date 2026-11-15. The schedule does not name a replacement. gpt-chat-latest-2026-05-05, gpt-chat-latest-2026-06-24 are stored with shutdown date 2026-11-17. The schedule does not name a replacement.
Last reviewed . Publisher: SunsetDiff.
Steps
Read the versions. The first table is every Azure OpenAI id in the dataset whose shutdown date is 2026-11-19. The replacement cell is the official replacement stored from the retirement schedule. Not published means that field is empty. Open the model page before you change a deployment.
List deployments on the resource. 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.
Read versionUpgradeOption. OnceCurrentVersionExpired upgrades the deployment when the retirement date is reached. null means the same thing. NoAutoUpgrade never upgrades, and that deployment stops working. Provisioned deployments are not auto-upgraded.
Call the named replacement. Where the table names gpt-5.6-sol or gpt-5.6-terra, deploy that version and send one real prompt before November 19, 2026. Where the cell says Not published, Microsoft did not name a replacement on the schedule.
Models retiring on November 19
These rows are every Azure OpenAI model in the dataset with shutdown date 2026-11-19. The model id links to its SunsetDiff model page. Deprecation date, shutdown date, and replacement are the fields stored on that row. Not published means the field is empty. These rows do not store a deprecation_date. The schedule's Lifecycle column says Deprecated for each of them.
The schedule says: "The Replacement column identifies Microsoft's recommended replacement and, where supported, the target for automatic upgrades at retirement." The replacement on each row is that column: gpt-5.6-sol or gpt-5.6-terra. This guide does not add a replacement the schedule does not print.
7 Azure OpenAI model ids with shutdown date 2026-11-19.
codex-mini on November 15 and gpt-chat-latest on November 17
codex-mini version 2025-05-16 is in the dataset with shutdown date 2026-11-15. The schedule lists it as Deprecated with retirement date 2026-11-15. The replacement cell on that row is empty, so the table says Not published.
These gpt-chat-latest rows are the ones whose stored shutdown date is 2026-11-17. The schedule lists both as Preview. The replacement cell is empty. The lifecycle page says: "Preview models aren't recommended for production workloads." It also says all preview deployments are either upgraded or terminated. And: "If no replacement exists, customers get 30 days notice before the model retires and inference returns 410 Gone." The schedule does not name a replacement, so this page does not pick the upgrade path or the no-replacement path for you.
Other gpt-chat-latest versions in the dataset have a different shutdown date, or none. The schedule does not name them as the replacement for the 2026-11-17 rows. gpt-chat-latest-2026-05-28: 2026-12-08. gpt-chat-latest-2026-08-06: 2027-01-12. gpt-chat-latest-2026-10-07: 2027-05-18.
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 batch of stored rows is Azure OpenAI shutdowns on November 19, 2026.
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."
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.
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 tables. o1 version 2024-12-17 is the dataset id o1-2024-12-17.
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 https://management.azure.com/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.CognitiveServices/accounts/{accountName}/deployments?api-version=2023-05-01
The base row for o4-mini version 2025-04-16 on the retirement schedule is Deprecated, retirement 2026-11-19, replacement gpt-5.6-terra. That is the shutdown date and replacement stored on the dataset row.
The schedule's fine-tuned table lists a different pair of dates for that same version: training retirement no earlier than 2027-05-19, deployment retirement 2027-11-19. The lifecycle page's fine-tuned table lists training retirement no earlier than 2027-04-16 and deployment retirement 2027-10-16. Those two Microsoft pages do not print the same fine-tune dates. SunsetDiff keeps both in the note on the model page and does not replace the base shutdown date with either one.
Both pages say: "For existing customers only. Otherwise, training retirement occurs at base model retirement." The base model retirement date on the schedule is 2026-11-19.
The schedule's replacement is the target for automatic upgrades where that is supported. Call gpt-5.6-sol or gpt-5.6-terra, the one on the same row, with the prompts you send now. Do that before November 19, 2026. A deployment set to NoAutoUpgrade will not move itself.
codex-mini and the two November 17 gpt-chat-latest versions have no replacement on the schedule. This guide does not name one.
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.
Which Azure OpenAI versions retire on November 19, 2026?
The dataset lists o1-2024-12-17, o1-pro-2025-03-19, o3-2025-04-16, o3-deep-research-2025-06-26, o3-mini-2025-01-31, o3-pro-2025-06-10, o4-mini-2025-04-16 with shutdown date 2026-11-19. The retirement schedule lists those versions as Deprecated with that retirement date.
What is the official replacement?
The recommended replacement is the official replacement stored on each row. o1-2024-12-17: gpt-5.6-sol. o1-pro-2025-03-19: gpt-5.6-sol. o3-2025-04-16: gpt-5.6-sol. o3-deep-research-2025-06-26: gpt-5.6-sol. o3-mini-2025-01-31: gpt-5.6-terra. o3-pro-2025-06-10: gpt-5.6-sol. o4-mini-2025-04-16: gpt-5.6-terra. The schedule says: "The Replacement column identifies Microsoft's recommended replacement and, where supported, the target for automatic upgrades at retirement."
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?
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.
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."
What about codex-mini and gpt-chat-latest?
codex-mini 2025-05-16 has shutdown date 2026-11-15 and no stored replacement. gpt-chat-latest-2026-05-05, gpt-chat-latest-2026-06-24 have shutdown date 2026-11-17 and no stored replacement. The lifecycle page says all preview deployments are either upgraded or terminated.
Does the o4-mini fine-tune date replace November 19, 2026?
No. The stored shutdown date is the base row, 2026-11-19, replacement gpt-5.6-terra. The schedule's fine-tune deployment date is 2027-11-19. The lifecycle page's fine-tune deployment date is 2027-10-16. Both pages say: "For existing customers only. Otherwise, training retirement occurs at base model retirement."