Deprecations

Overview

As we launch safer and more capable models, we regularly retire older models. Software relying on OpenAI models may need occasional updates to keep working. Impacted customers will always be notified by email and in our documentation.

Each model has one of three lifecycle states.

• Active. You can use the model through the API. OpenAI hasn’t announced its retirement.
• Deprecated. OpenAI has announced the model’s retirement. You can still use it until its shutdown date.
• Shutdown. The model no longer accepts requests through the standard API.

For deprecation notice periods and help migrating to a replacement model, see the deprecation policy and migration guidance below.

Upcoming deprecations

Fine-tuned versions of the models listed above follow the same shutdown schedule as their underlying base models.

For speech migrations, see the Realtime API guide and the transcription guide.

Model deprecation notice periods

We provide advance notice before retiring models so customers have time to plan and migrate. When we announce a model deprecation, we notify customers who are actively using the model by email and document the deprecation on this page.

Unless safety or compliance concerns require a faster timeline, we provide the following minimum notice periods before model retirement:

• Generally available models: At least 6 months.
• Specialized variants of generally available models and image generation models: At least 3 months. Examples include chat variants such as gpt-5.1-chat-latest, Codex variants such as gpt-5.3-codex, and deep research variants such as o3-deep-research.
• Preview models: Preview models, identified by preview in the model name, may be retired with much shorter notice, such as 2 weeks. Examples include computer-use-preview and gpt-4o-audio-preview. We don’t recommend using preview models for business-critical production workloads unless you can migrate on short notice.

These notice periods give customers time to evaluate recommended replacement models, test application behavior, and complete migrations before a model is no longer available. In some cases, developers may be able to provision dedicated capacity for continued access after a model’s shutdown date. To explore this option, contact our sales team.

Best practices

• Check the documentation regularly for model deprecation updates.
• To monitor model shutdowns programmatically, call the List models endpoint (GET /v1/models) and check each model’s optional shutdown_date field. The field is also available from the Retrieve a model endpoint.

Migration guidance

• In Codex, invoke the OpenAI Docs skill with $openai-docs and ask it to migrate your project to the recommended replacement.
• See the GPT-6 migration guide.
• Run representative requests against both models. Compare outputs, latency, and cost before switching production traffic to the replacement.

Update to OpenAI’s self-serve fine-tuning

On May 7th, 2026, we notified developers using OpenAI’s self-serve fine-tuning platform of updates to availability.

Inference on fine-tuned models will continue to be available until the base models are deprecated.