// AI Platform Drift
OpenAI deprecations page restructured into a single table of model and feature shutdowns through April 2027
OpenAI deprecations · published 2026-11-14 18:03 UTC
CORRECTED 2026-11-16 16:11 UTC — Correction, 16 November 2026: This item had three errors. Its advice gave 11 December 2026 as the migration date for the image models; OpenAI's table lists gpt-image-1-mini, gpt-image-1.5 and chatgpt-image-latest with a shutdown date of December 1, 2026, and 11 December applies to the gpt-5 family, o3 and o3-pro. It called these models and four feature deprecations new entries; they were already on the page, with notices dated between May 7 and June 11, 2026, and this change moved them into a table. It gave the table 31 entries; the model table has 34 rows. The action date stored with this item, 1 December 2026, was correct.
Stood 46h 8m · cause triage miss · every correction ↗
WHAT CHANGEDThe deprecations page moved from announcement-driven sections to a single table listing shutdown dates, affected models, status, replacements and notice dates. The model table has 34 rows with shutdown dates from 1 December 2026 through 1 April 2027. These are not new deprecations: the page already listed them in dated announcement sections, and the table's notice dates run from 2 June 2026 to 10 November 2026. The nearest are the image models (gpt-image-1-mini, gpt-image-1.5, chatgpt-image-latest) on 1 December 2026 and the gpt-5 family and o3 models (gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro, o3, o3-pro) on 11 December 2026. Replacements are specified: gpt-6.1-sol for gpt-5, gpt-6.1-terra for gpt-5-mini, gpt-6-luna for gpt-5-nano. The page removed blog post notification language and detailed announcement sections, added lifecycle state definitions (Active, Deprecated, Shutdown), and moved programmatic monitoring guidance to a Best practices section.
WHY IT MATTERSThe restructure consolidates all deprecation information into a single scannable table, making it easier to identify which models your application uses and when they shut down. The new format surfaces notice dates and shutdown dates side-by-side, clarifying how much time remains before each retirement. The addition of lifecycle states standardizes how OpenAI communicates model availability. The removal of announcement-driven sections means you must now check the table directly rather than reading chronological updates.
WHAT TO DOCheck the table for every model identifier your application calls. For each deprecated model, note its shutdown date and replacement. If you use gpt-image-1-mini, gpt-image-1.5 or chatgpt-image-latest, migrate to gpt-image-2.6-sunburst or gpt-image-2.6-flare before 1 December 2026. If you use gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro, o3 or o3-pro, schedule migration to the specified replacement before 11 December 2026. If you use /v1/prompts, the Evals dashboard, Agent Builder, or self-serve fine-tuning, review the linked migration guides before 30 November 2026 or 6 January 2027. Add the List models endpoint (GET /v1/models) to your monitoring to check the shutdown_date field programmatically.
Original text (as first published, superseded)
HEADLINEOpenAI deprecations page restructured with 31 model and feature shutdowns through April 2027
WHAT CHANGEDThe deprecations page moved from announcement-driven sections to a single table listing shutdown dates, affected models, status, replacements and notice dates. The table now includes 31 upcoming deprecations with shutdown dates from 1 December 2026 through 1 April 2027. New entries include gpt-5 family models (gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro), o3 models (o3, o3-pro), image models (gpt-image-1-mini, gpt-image-1.5, chatgpt-image-latest), and feature deprecations (/v1/prompts, Evals dashboard, Agent Builder, self-serve fine-tuning job creation). Replacements are specified: gpt-6.1-sol for gpt-5, gpt-6.1-terra for gpt-5-mini, gpt-6-luna for gpt-5-nano. The page removed blog post notification language and detailed announcement sections, added lifecycle state definitions (Active, Deprecated, Shutdown), and moved programmatic monitoring guidance to a Best practices section.
WHAT TO DOCheck the table for every model identifier your application calls. For each deprecated model, note its shutdown date and replacement. If you use gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro, o3, o3-pro, or any of the image models listed, schedule migration to the specified replacement before 11 December 2026. If you use /v1/prompts, the Evals dashboard, Agent Builder, or self-serve fine-tuning, review the linked migration guides before 30 November 2026 or 6 January 2027. Add the List models endpoint (GET /v1/models) to your monitoring to check the shutdown_date field programmatically.
TRIAGE SIGNALnew models added to deprecation list: gpt-image-1-mini, gpt-image-1.5, chatgpt-image-latest, gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro, o3, o3-pro all with Dec 11 2026 shutdown
TRIAGE SIGNALnew feature deprecations added: /v1/prompts, Evals dashboard, Agent Builder, self-serve fine-tuning job creation
TRIAGE REASONINGMultiple future model shutdowns with specific dates and new deprecations announced; engineering teams must plan migrations.
Model-reported confidence 85% (not measured accuracy)
Primary source ↗
written by anthropic/claude-sonnet-4.5
Show the reasoning — raw diff, triage verdict, confidence
RAW DIFF
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 along with blog posts for larger changes. +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. -This page lists all API deprecations, along with recommended replacements. +Each model has one of three lifecycle states. -To monitor model shutdowns programmatically, call the List models endpoint (GET /v1/models) and check each model’s optional shutdown_date field. When present, this field contains the shutdown date as a YYYY-MM-DD string, or null if no shutdown date has been announced; the field is also available from the Retrieve a model endpoint. +Active. You can use the model through the API. OpenAI hasn’t announced its retirement. -Model deprecation notice periods +Deprecated. OpenAI has announced the model’s retirement. You can still use it until its shutdown date. -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. +Shutdown. The model no longer accepts requests through the standard API. -Unless safety or compliance concerns require a faster timeline, we provide the following minimum notice periods before model retirement: +For deprecation notice periods and help migrating to a replacement model, see the deprecation policy and migration guidance below. -Generally available models: At least 6 months. +See feature and endpoint deprecations for other upcoming API shutdowns. -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. - -If safety or compliance concerns require us to retire a model sooner, we will provide as much notice as reasonably possible. - -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. - -Deprecation vs. legacy - -We use the term “deprecation” to refer to the process of retiring a model or endpoint. When we announce that a model or endpoint is being deprecated, it immediately becomes deprecated. All deprecated models and endpoints will also have a shut down date. At the time of the shut down, the model or endpoint will no longer be accessible. - -We use the terms “sunset” and “shut down” interchangeably to mean a model or endpoint is no longer accessible. - -We use the term “legacy” to refer to models and endpoints that no longer receive updates. We tag endpoints and models as legacy to signal to developers where we’re moving as a platform and that they should likely migrate to newer models or endpoints. You can expect that a legacy model or endpoint will be deprecated at some point in the future. - Upcoming deprecations -Upcoming deprecations are listed below, with the most recent announcements at the top. - -2026-11-10: GPT Image 2 - -The gpt-image-2 model and gpt-image-2-2026-04-21 snapshot are deprecated and will be removed from the API on February 10, 2027. - Shutdown date -Model / system +Affected model +Status Recommended replacement +Notice date -February 10, 2027 -gpt-image-2 | gpt-image-2-2026-04-21 +Dec 1, 2026 +gpt-image-1-mini +Deprecated gpt-image-2.6-sunburst or gpt-image-2.6-flare +Jun 2, 2026 -2026-11-05: GPT-5.5-Cyber +Dec 1, 2026 +gpt-image-1.5, gpt-image-1.5-2025-12-16 +Deprecated +gpt-image-2.6-sunburst or gpt-image-2.6-flare +Jun 2, 2026 -The gpt-5.5-cyber-preview model is deprecated and will be removed from the API on February 1, 2027. Migrate to the most capable cyber model available to you before the shutdown date. +Dec 1, 2026 +chatgpt-image-latest +Deprecated +gpt-image-2.6-sunburst or gpt-image-2.6-flare +Jun 2, 2026 -Shutdown date -Model / system -Recommended replacement +Dec 11, 2026 +gpt-5, gpt-5-2025-08-07 +Deprecated +gpt-6.1-sol +Jun 11, 2026 -February 1, 2027 -gpt-5.5-cyber-preview -The most capable cyber model available to you. +Dec 11, 2026 +gpt-5-mini, gpt-5-mini-2025-08-07 +Deprecated +gpt-6.1-terra +Jun 11, 2026 -2026-10-14: GPT-4 series model deprecations - -On October 14, 2026, we notified developers using certain GPT-4 series models of their deprecation and removal from the API on January 14, 2027. - -Shutdown date -Model / system -Recommended replacement - -January 14, 2027 -GPT-4o (gpt-4o-2024-08-06, gpt-4o-2024-11-20) +Dec 11, 2026 +gpt-5-nano, gpt-5-nano-2025-08-07 +Deprecated gpt-6-luna +Jun 11, 2026 -January 14, 2027 -GPT-4o mini (gpt-4o-mini-2024-07-18) -gpt-6-luna +Dec 11, 2026 +gpt-5-pro, gpt-5-pro-2025-10-06 +Deprecated +gpt-6.1-sol (reasoning.mode: pro) in the Responses API +Jun 11, 2026 -January 14, 2027 -GPT-4.1 (gpt-4.1-2025-04-14) -gpt-6-luna +Dec 11, 2026 +o3, o3-2025-04-16 +Deprecated +gpt-6.1-sol +Jun 11, 2026 -January 14, 2027 -GPT-4.1 mini (gpt-4.1-mini-2025-04-14) -gpt-6-luna +Dec 11, 2026 +o3-pro, o3-pro-2025-06-10 +Deprecated +gpt-6.1-sol (reasoning.mode: pro) in the Responses API +Jun 11, 2026 -Fine-tuned versions of these models follow the same shutdown schedule as their underlying base models. - -2026-10-01: GPT-5.3-Codex, GPT-5.1, GPT-5.4-Nano - -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. - -Shutdown date -Model / system -Recommended replacement - -Apr 1, 2027 -gpt-5.3-codex -gpt-6-sol - -Apr 1, 2027 -gpt-5.4-nano | gpt-5.4-nano-2026-03-17 -gpt-6-luna - -Apr 1, 2027 -gpt-5.1 | gpt-5.1-2025-11-13 -gpt-6-sol - -2026-10-01: Text-to-speech models - -The following text-to-speech models are deprecated and will be removed from the API on January 6, 2027, with at least three months’ notice. Migrate to gpt-realtime-2.1-mini before the shutdown date. See the Realtime API guide to plan your migration. - -Shutdown date -Model / system -Recommended replacement - Jan 6, 2027 tts-1 +Deprecated gpt-realtime-2.1-mini +Oct 1, 2026 Jan 6, 2027 tts-1-hd +Deprecated gpt-realtime-2.1-mini +Oct 1, 2026 Jan 6, 2027 -gpt-4o-mini-tts | gpt-4o-mini-tts-2025-03-20 +gpt-4o-mini-tts, gpt-4o-mini-tts-2025-03-20, gpt-4o-mini-tts-2025-12-15 +Deprecated gpt-realtime-2.1-mini +Oct 1, 2026 -Jan 6, 2027 -gpt-4o-mini-tts | gpt-4o-mini-tts-2025-12-15 -gpt-realtime-2.1-mini +Jan 14, 2027 +GPT-4o (gpt-4o-2024-08-06, gpt-4o-2024-11-20) +Deprecated +gpt-6-luna +Oct 14, 2026 -2026-08-26: Transcription models +Jan 14, 2027 +GPT-4o mini (gpt-4o-mini-2024-07-18) +Deprecated +gpt-6-luna +Oct 14, 2026 -On August 26, 2026, we notified developers using whisper-1, gpt-4o-transcribe, gpt-4o-mini-transcribe, and gpt-4o-transcribe-diarize of their deprecation and removal from the API on February 26, 2027. +Jan 14, 2027 +GPT-4.1 (gpt-4.1-2025-04-14) +Deprecated +gpt-6-luna +Oct 14, 2026 -For information about the recommended replacements, see the transcription guide. +Jan 14, 2027 +GPT-4.1 mini (gpt-4.1-mini-2025-04-14) +Deprecated +gpt-6-luna +Oct 14, 2026 -Shutdown date -Model / system -Recommended replacement - -Feb 26, 2027 -whisper-1 -gpt-live-transcribe or gpt-transcribe - -Feb 26, 2027 -gpt-4o-transcribe -gpt-live-transcribe or gpt-transcribe - -Feb 26, 2027 -gpt-4o-mini-transcribe | gpt-4o-mini-transcribe-2025-12-15 -gpt-live-transcribe or gpt-transcribe - -Feb 26, 2027 -gpt-4o-transcribe-diarize -gpt-live-transcribe or gpt-transcribe - -Feb 26, 2027 -/v1/audio/translations -v1/realtime/translations - -2026-07-20: Legacy audio, realtime, and transcription models - -On July 20, 2026, we notified developers using legacy audio, realtime, and transcription model families and snapshots of their deprecation and removal from the API on January 20, 2027. - -Shutdown date -Model family / snapshot -Recommended replacement - Jan 20, 2027 -gpt-realtime | gpt-realtime-2025-08-28 +gpt-realtime, gpt-realtime-2025-08-28 +Deprecated gpt-realtime-2.1 +Jul 20, 2026 Jan 20, 2027 -gpt-audio | gpt-audio-2025-08-28 +gpt-audio, gpt-audio-2025-08-28 +Deprecated gpt-audio-1.5 +Jul 20, 2026 Jan 20, 2027 gpt-4o-audio +Deprecated gpt-audio-1.5 +Jul 20, 2026 Jan 20, 2027 gpt-4o-realtime +Deprecated gpt-realtime-2.1 +Jul 20, 2026 Jan 20, 2027 -gpt-realtime-mini | gpt-realtime-mini-2025-12-15 +gpt-realtime-mini, gpt-realtime-mini-2025-12-15 +Deprecated gpt-realtime-2.1-mini +Jul 20, 2026 Jan 20, 2027 -gpt-audio-mini | gpt-audio-mini-2025-12-15 +gpt-audio-mini, gpt-audio-mini-2025-12-15 +Deprecated gpt-audio-1.5 +Jul 20, 2026 Jan 20, 2027 gpt-4o-mini-realtime +Deprecated gpt-realtime-2.1-mini +Jul 20, 2026 Jan 20, 2027 gpt-4o-mini-audio +Deprecated gpt-audio-1.5 +Jul 20, 2026 Jan 20, 2027 gpt-4o-mini-transcribe-2025-03-20 +Deprecated gpt-4o-mini-transcribe-2025-12-15 +Jul 20, 2026 -2026-06-11: GPT-5 and o3 model deprecations +Feb 1, 2027 +gpt-5.5-cyber-preview +Deprecated +The most capable cyber model available to you. +Nov 5, 2026 -On June 11, 2026, we notified developers using older GPT-5 and o3 model snapshots of their deprecation and removal from the API on December 11, 2026. +Feb 10, 2027 +gpt-image-2, gpt-image-2-2026-04-21 +Deprecated +gpt-image-2.6-sunburst or gpt-image-2.6-flare +Nov 10, 2026 -Shutdown date -Model / system -Recommended replacement +Feb 26, 2027 +whisper-1 +Deprecated +gpt-live-transcribe or gpt-transcribe +Aug 26, 2026 -Dec 11, 2026 -gpt-5 | gpt-5-2025-08-07 -gpt-5.6-sol +Feb 26, 2027 +gpt-4o-transcribe +Deprecated +gpt-live-transcribe or gpt-transcribe +Aug 26, 2026 -Dec 11, 2026 -gpt-5-mini | gpt-5-mini-2025-08-07 -gpt-5.6-terra +Feb 26, 2027 +gpt-4o-mini-transcribe, gpt-4o-mini-transcribe-2025-12-15 +Deprecated +gpt-live-transcribe or gpt-transcribe +Aug 26, 2026 -Dec 11, 2026 -gpt-5-nano | gpt-5-nano-2025-08-07 -gpt-5.6-luna +Feb 26, 2027 +gpt-4o-transcribe-diarize +Deprecated +gpt-live-transcribe or gpt-transcribe +Aug 26, 2026 -Dec 11, 2026 -gpt-5-pro | gpt-5-pro-2025-10-06 -gpt-5.6-sol (reasoning.mode: pro) +Apr 1, 2027 +gpt-5.3-codex +Deprecated +gpt-6-sol +Oct 1, 2026 -Dec 11, 2026 -o3 | o3-2025-04-16 -gpt-5.6-sol +Apr 1, 2027 +gpt-5.4-nano, gpt-5.4-nano-2026-03-17 +Deprecated +gpt-6-luna +Oct 1, 2026 -Dec 11, 2026 -o3-pro | o3-pro-2025-06-10 -gpt-5.6-sol (reasoning.mode: pro) +Apr 1, 2027 +gpt-5.1, gpt-5.1-2025-11-13 +Deprecated +gpt-6-sol +Oct 1, 2026 -Fine-tuned versions of these models follow the same shutdown schedule as their underlying base models. +Fine-tuned versions of the models listed above follow the same shutdown schedule as their underlying base models. -2026-06-03: Reusable prompts +For speech migrations, see the Realtime API guide and the transcription guide. -On June 3, 2026, we notified developers using reusable prompts in the dashboard and API that reusable prompt objects are being deprecated. +Feature and endpoint deprecations -Date -Update +Shutdown date +Affected feature or endpoint +Status +Recommended replacement +Notice date -June 3, 2026 -Deprecation announced and prompt creation de-emphasized in the platform. +Nov 30, 2026 +/v1/prompts and reusable prompt objects +Deprecated +Move prompt content into your application code. Migration guide +Jun 3, 2026 Nov 30, 2026 -The v1/prompts API and reusable prompt objects are scheduled to shut down. +Evals dashboard, API, and graders for eval workflows +Read-only +Migrate to Promptfoo. For fine-tuning graders, see the fine-tuning timeline. +Jun 3, 2026 -To migrate, move reusable prompt content into your application code. See Migrate from prompt objects. +Nov 30, 2026 +Agent Builder +Deprecated +Agents SDK or ChatGPT Workspace Agents. Migration guide. ChatKit remains available. +Jun 3, 2026 -2026-06-03: Evals platform +Jan 6, 2027 +Self-serve fine-tuning job creation +Restricted access +See the fine-tuning timeline. +May 7, 2026 -On June 3, 2026, we notified developers using the Evals platform that the product is being deprecated. +Feb 26, 2027 +/v1/audio/translations +Deprecated +/v1/realtime/translations +Aug 26, 2026 -Date -Update +Model deprecation notice periods -June 3, 2026 -Deprecation announced for the Evals platform. +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. -Oct 31, 2026 -Existing evals become read-only. +Unless safety or compliance concerns require a faster timeline, we provide the following minimum notice periods before model retirement: -Nov 30, 2026 -The Evals dashboard and API are scheduled to shut down. +Generally available models: At least 6 months. -Graders documented for eval workflows are part of this transition. Fine-tuning-related timelines remain covered in the self-serve fine-tuning section below. +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. -See Moving from OpenAI Evals to Promptfoo for a migration path. +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. -2026-06-03: Agent Builder +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. -On June 3, 2026, we notified developers using Agent Builder that the product is being deprecated. ChatKit remains available. +Best practices -Date -Update +Check the documentation regularly for model deprecation updates. -June 3, 2026 -Deprecation announced for Agent Builder. +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. -Nov 30, 2026 -Agent Builder is scheduled to shut down. +Migration guidance -See Migrate from Agent Builder to continue with the Agents SDK or ChatGPT Workspace Agents. +In Codex, invoke the OpenAI Docs skill with $openai-docs and ask it to migrate your project to the recommended replacement. -2026-06-02: GPT Image model deprecations +See the GPT-6 migration guide. -On June 2, 2026, we notified developers using older GPT Image models of their deprecation and removal from the API on December 1, 2026. +Run representative requests against both models. Compare outputs, latency, and cost before switching production traffic to the replacement. -Shutdown date -Model / system -Recommended replacement - -Dec 1, 2026 -gpt-image-1-mini -gpt-image-2.6-sunburst or gpt-image-2.6-flare - -Dec 1, 2026 -gpt-image-1.5 | gpt-image-1.5-2025-12-16 -gpt-image-2.6-sunburst or gpt-image-2.6-flare - -Dec 1, 2026 -chatgpt-image-latest -gpt-image-2.6-sunburst or gpt-image-2.6-flare - 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. @@ Past deprecations -Past deprecations are listed below, with the most recent announcements at the top. - -2026-09-11: GPT-5.4-Cyber - -The gpt-5.4-cyber model is deprecated and will be removed from the API on October 1, 2026. Migrate to the most capable cyber model available to you before the shutdown date. - Shutdown date -Model / system -Recommended replacement +Affected model or feature +Listed replacement +Notice date -Oct 1, 2026 -gpt-5.4-cyber -The most capable cyber model available to you. - -2026-05-08: gpt-5.2-chat-latest and gpt-5.3-chat-latest model snapshots - -On May 8th, 2026, we notified developers using gpt-5.2-chat-latest and gpt-5.3-chat-latest model snapshots of their deprecation and removal from the API. - -Shutdown date -Model / system -Recommended replacement - -Aug 10, 2026 -gpt-5.2-chat-latest -gpt-5.6-sol - -Aug 10, 2026 -gpt-5.3-chat-latest -gpt-5.6-sol - -2026-04-22: Legacy GPT model snapshots - -On April 22, 2026, we announced the deprecation of the following older OpenAI models. Access to these models was shut down on October 23, 2026. - -Shutdown date -Model snapshot -Substitute model - -October 23, 2026 -gpt-3.5-turbo-0125 | gpt-3.5-turbo, gpt-3.5-turbo-completions +Oct 23, 2026 +gpt-3.5-turbo-0125, gpt-3.5-turbo, gpt-3.5-turbo-completions gpt-5.6-terra +Apr 22, 2026 -October 23, 2026 -gpt-4-0613 | gpt-4, gpt-4-0613-completions, gpt-4-completions +Oct 23, 2026 +gpt-4-0613, gpt-4, gpt-4-0613-completions, gpt-4-completions gpt-5.6-sol +Apr 22, 2026 -October 23, 2026 +Oct 23, 2026 gpt-4-1106-preview gpt-5.6-sol +Apr 22, 2026 -October 23, 2026 -gpt-4-turbo | gpt-4-turbo-2024-04-09, gpt-4-turbo-completions +Oct 23, 2026 +gpt-4-turbo, gpt-4-turbo-2024-04-09, gpt-4-turbo-completions gpt-5.6-sol +Apr 22, 2026 -October 23, 2026 -gpt-4.1-nano | gpt-4.1-nano-2025-04-14 +Oct 23, 2026 +gpt-4.1-nano, gpt-4.1-nano-2025-04-14 gpt-5.6-luna +Apr 22, 2026 -October 23, 2026 +Oct 23, 2026 gpt-4o-2024-05-13 gpt-5.6-sol +Apr 22, 2026 -October 23, 2026 +Oct 23, 2026 gpt-image-1 gpt-image-2.5-sunburst or gpt-image-2.5-flare +Apr 22, 2026 -October 23, 2026 -o1-2024-12-17 | o1 +Oct 23, 2026 +o1-2024-12-17, o1 gpt-5.6-sol +Apr 22, 2026 -October 23, 2026 -o1-pro-2025-03-19 | o1-pro +Oct 23, 2026 +o1-pro-2025-03-19, o1-pro gpt-5.6-sol (reasoning.mode: pro) +Apr 22, 2026 -October 23, 2026 -o3-mini-2025-01-31 | o3-mini +Oct 23, 2026 +o3-mini-2025-01-31, o3-mini gpt-5.6-sol +Apr 22, 2026 -October 23, 2026 +Oct 23, 2026 ft-o4-mini-2025-04-16 gpt-5.6-terra +Apr 22, 2026 -October 23, 2026 -o4-mini-2025-04-16 | o4-mini +Oct 23, 2026 +o4-mini-2025-04-16, o4-mini gpt-5.6-terra +Apr 22, 2026 -Fine-tuned versions of these models follow the same shutdown schedule as their underlying base models. +Oct 1, 2026 +gpt-5.4-cyber +The most capable cyber model available to you. +Sep 11, 2026 -2026-04-22: Legacy GPT model snapshots (July 2026 shutdown) +Sep 28, 2026 +gpt-3.5-turbo-instruct +gpt-5.6-terra +Sep 26, 2025 -On April 22, 2026, we announced the deprecation of the following older OpenAI models. Access to these models was shut down on July 23, 2026. +Sep 28, 2026 +babbage-002 +gpt-5.6-terra +Sep 26, 2025 -Shutdown date -Model snapshot -Substitute model +Sep 28, 2026 +davinci-002 +gpt-5.6-terra +Sep 26, 2025 -July 23, 2026 -computer-use-preview-2025-03-11 | computer-use-preview +Sep 28, 2026 +gpt-3.5-turbo-1106 gpt-5.6-terra +Sep 26, 2025 -July 23, 2026 +Sep 24, 2026 +Videos API +No one-to-one replacement +Mar 24, 2026 + +Sep 24, 2026 +sora-2 +No one-to-one replacement +Mar 24, 2026 + +Sep 24, 2026 +sora-2-pro +No one-to-one replacement +Mar 24, 2026 + +Sep 24, 2026 +sora-2-2025-10-06 +No one-to-one replacement +Mar 24, 2026 + +Sep 24, 2026 +sora-2-2025-12-08 +No one-to-one replacement +Mar 24, 2026 + +Sep 24, 2026 +sora-2-pro-2025-10-06 +No one-to-one replacement +Mar 24, 2026 + +Aug 26, 2026 +Assistants API +Responses API and Conversations API (migration guide) +Aug 26, 2025 + +Aug 10, 2026 +gpt-5.2-chat-latest +gpt-5.6-sol +May 8, 2026 + +Aug 10, 2026 +gpt-5.3-chat-latest +gpt-5.6-sol +May 8, 2026 + +Jul 23, 2026 +computer-use-preview-2025-03-11, computer-use-preview +gpt-5.6-terra +Apr 22, 2026 + +Jul 23, 2026 gpt-4o-mini-search-preview-2025-03-11 gpt-5.6-terra +Apr 22, 2026 -July 23, 2026 +Jul 23, 2026 gpt-4o-search-preview-2025-03-11 gpt-5.6-terra +Apr 22, 2026 -July 23, 2026 +Jul 23, 2026 gpt-5-chat-latest gpt-5.6-sol +Apr 22, 2026 -July 23, 2026 +Jul 23, 2026 gpt-5-codex gpt-5.6-sol +Apr 22, 2026 -July 23, 2026 +Jul 23, 2026 gpt-5.1-chat-latest gpt-5.6-sol +Apr 22, 2026 -July 23, 2026 +Jul 23, 2026 gpt-5.1-codex gpt-5.6-sol +Apr 22, 2026 -July 23, 2026 +Jul 23, 2026 gpt-5.1-codex-max gpt-5.6-sol +Apr 22, 2026 -July 23, 2026 +Jul 23, 2026 gpt-5.1-codex-mini gpt-5.6-terra +Apr 22, 2026 -July 23, 2026 +Jul 23, 2026 gpt-audio-mini-2025-10-06 gpt-audio-1.5 +Apr 22, 2026 -July 23, 2026 +Jul 23, 2026 gpt-realtime-mini-2025-10-06 gpt-realtime-2.1-mini +Apr 22, 2026 -July 23, 2026 -o3-deep-research-2025-06-26 | o3-deep-research +Jul 23, 2026 +o3-deep-research-2025-06-26, o3-deep-research gpt-5.6-sol +Apr 22, 2026 -July 23, 2026 -o4-mini-deep-research-2025-06-26 | o4-mini-deep-research +Jul 23, 2026 +o4-mini-deep-research-2025-06-26, o4-mini-deep-research gpt-5.6-sol +Apr 22, 2026 -July 23, 2026 +Jul 23, 2026 gpt-5.2-codex gpt-5.6-sol +Apr 22, 2026 -2026-03-24: Sora 2 video generation models and Videos API - -On March 24th, 2026, we notified developers using the Videos API and Sora 2 video generation model aliases and snapshots of their deprecation and removal from the API on September 24, 2026. - -Shutdown date -Model / system -Recommended replacement - -2026-09-24 -Videos API -— - -2026-09-24 -sora-2 -— - -2026-09-24 -sora-2-pro -— - -2026-09-24 -sora-2-2025-10-06 -— - -2026-09-24 -sora-2-2025-12-08 -— - -2026-09-24 -sora-2-pro-2025-10-06 -— - -2025-11-18: chatgpt-4o-latest snapshot - -On November 18th, 2025, we notified developers using chatgpt-4o-latest model snapshot of its deprecation and removal from the API on February 17, 2026. - -Shutdown date -Model / system -Recommended replacement - -2026-02-17 -chatgpt-4o-latest -gpt-5.1-chat-latest - -2025-11-17: codex-mini-latest model snapshot - -On November 17th, 2025, we notified developers using codex-mini-latest model of its deprecation and removal from the API on February 12, 2026. As part of this deprecation, we will no longer support our legacy local shell tool, which is only available for use with codex-mini-latest. For new use cases, please use our latest shell tool. - -Shutdown date -Model / system -Recommended replacement - -2026-02-12 -codex-mini-latest -gpt-5-codex-mini - -2025-11-14: DALL·E model snapshots - -On November 14th, 2025, we notified developers using DALL·E model snapshots of their deprecation and removal from the API on May 12, 2026. - -Shutdown date -Model / system -Recommended replacement - -2026-05-12 +May 12, 2026 dall-e-2 gpt-image-2, gpt-image-1, or gpt-image-1-mini +Nov 14, 2025 -2026-05-12 +May 12, 2026 dall-e-3 gpt-image-2, gpt-image-1, or gpt-image-1-mini +Nov 14, 2025 -2025-09-26: Legacy GPT model snapshots - -To improve reliability and make it easier for developers to choose the right models, we deprecated a set of older OpenAI models with declining usage. Access to these models was shut down on September 28, 2026. - -Shutdown date -Model / system -Recommended replacement - -2026-09-28 -gpt-3.5-turbo-instruct -gpt-5.6-terra - -2026-09-28 -babbage-002 -gpt-5.6-terra - -2026-09-28 -davinci-002 -gpt-5.6-terra - -2026-09-28 -gpt-3.5-turbo-1106 -gpt-5.6-terra - -2025-09-26: Legacy GPT model snapshots (March 2026 shutdown) - -To improve reliability and make it easier for developers to choose the right models, we deprecated a set of older OpenAI models with declining usage. Access to these models was shut down on March 26, 2026. - -Shutdown date -Model / system -Recommended replacement - -2026‐03‐26 -gpt-4-0314 -gpt-5 or gpt-4.1* - -2026‐03‐26 -gpt-4-0125-preview (including gpt-4-turbo-preview and gpt-4-turbo-preview-completions, which point to this snapshot) -gpt-5 or gpt-4.1* - -*For tasks that are especially latency sensitive and don’t require reasoning - -2025-09-15: Realtime API Beta - -The Realtime API Beta was deprecated and removed from the API on May 12, 2026. - -The interfaces in the Realtime beta API and the released GA API have a few key differences. See the migration guide for the current GA interface and related Realtime docs. - -Shutdown date -Model / system -Recommended replacement - -2026‐05‐12 +May 12, 2026 OpenAI-Beta: realtime=v1 -Realtime API +Realtime API migration guide +Sep 15, 2025 -2025-09-15: gpt-4o-realtime-preview models - -In September, 2025, we notified developers using gpt-4o-realtime-preview models of their deprecation and removal from the API in six months. - -Shutdown date -Model / system -Recommended replacement - -2026-05-07 +May 7, 2026 gpt-4o-realtime-preview gpt-realtime-1.5 +Sep 15, 2025 -2026-05-07 +May 7, 2026 gpt-4o-realtime-preview-2025-06-03 gpt-realtime-1.5 +Sep 15, 2025 -2026-05-07 +May 7, 2026 gpt-4o-realtime-preview-2024-12-17 gpt-realtime-1.5 +Sep 15, 2025 -2026-05-07 +May 7, 2026 gpt-4o-mini-realtime-preview gpt-realtime-mini +Sep 15, 2025 -2026-05-07 +May 7, 2026 gpt-4o-audio-preview gpt-audio-1.5 +Sep 15, 2025 -2026-05-07 +May 7, 2026 gpt-4o-mini-audio-preview gpt-audio-mini +Sep 15, 2025 -2025-08-20: Assistants API +Mar 26, 2026 +gpt-4-0314 +gpt-5, or gpt-4.1 for latency-sensitive tasks that don’t require reasoning +Sep 26, 2025 -On August 26th, 2025, we notified developers using the Assistants API of its deprecation and removal from the API one year later, on August 26, 2026. +Mar 26, 2026 +gpt-4-0125-preview (including gpt-4-turbo-preview and gpt-4-turbo-preview-completions, which point to this snapshot) +gpt-5, or gpt-4.1 for latency-sensitive tasks that don’t require reasoning +Sep 26, 2025 -When we released the Responses API in March 2025, we announced plans to bring all Assistants API features to the easier to use Responses API, with a sunset date in 2026. +Feb 17, 2026 +chatgpt-4o-latest +gpt-5.1-chat-latest +Nov 18, 2025 -See the Assistants to Conversations migration guide to learn more about how to migrate your current integration to the Responses API and Conversations API. +Feb 12, 2026 +codex-mini-latest +gpt-5-codex-mini +Nov 17, 2025 -Shutdown date -Model / system -Recommended replacement - -2026‐08‐26 -Assistants API -Responses API and Conversations API - -2025-06-10: gpt-4o-realtime-preview-2024-10-01 - -On June 10th, 2025, we notified developers using gpt-4o-realtime-preview-2024-10-01 of its deprecation and removal from the API in three months. - -Shutdown date -Model / system -Recommended replacement - -2025-10-10 -gpt-4o-realtime-preview-2024-10-01 -gpt-realtime-1.5 - -2025-06-10: gpt-4o-audio-preview-2024-10-01 - -On June 10th, 2025, we notified developers using gpt-4o-audio-preview-2024-10-01 of its deprecation and removal from the API in three months. - -Shutdown date -Model / system -Recommended replacement - -2025-10-10 -gpt-4o-audio-preview-2024-10-01 -gpt-audio-1.5 - -2025-04-28: text-moderation - -On April 28th, 2025, we notified developers using text-moderation of its deprecation and removal from the API in six months. - -Shutdown date -Model / system -Recommended replacement - -2025-10-27 +Oct 27, 2025 text-moderation-007 omni-moderation +Apr 28, 2025 -2025-10-27 +Oct 27, 2025 text-moderation-stable omni-moderation +Apr 28, 2025 -2025-10-27 +Oct 27, 2025 text-moderation-latest omni-moderation +Apr 28, 2025 -2025-04-28: o1-preview and o1-mini +Oct 27, 2025 +o1-mini +o4-mini +Apr 28, 2025 -On April 28th, 2025, we notified developers using o1-preview and o1-mini of their deprecations and removal from the API in three months and six months respectively. +Oct 10, 2025 +gpt-4o-realtime-preview-2024-10-01 +gpt-realtime-1.5 +Jun 10, 2025 -Shutdown date -Model / system -Recommended replacement +Oct 10, 2025 +gpt-4o-audio-preview-2024-10-01 +gpt-audio-1.5 +Jun 10, 2025 -2025-07-28 +Jul 28, 2025 o1-preview o3 +Apr 28, 2025 -2025-10-27 -o1-mini -o4-mini - -2025-04-14: GPT-4.5-preview - -On April 14th, 2025, we notified developers that the gpt-4.5-preview model is deprecated and will be removed from the API in the coming months. - -Shutdown date -Model / system -Recommended replacement - -2025-07-14 +Jul 14, 2025 gpt-4.5-preview gpt-4.1 +Apr 14, 2025 -2024-10-02: Assistants API beta v1 +Jun 6, 2025 +gpt-4-32k Historical price $60.00 / 1M input tokens + $120 / 1M output tokens +gpt-4o +Jun 6, 2024 -In April 2024 when we released the v2 beta version of the Assistants API, we announced that access to the v1 beta would be shut off by the end of 2024. Access to the v1 beta will be discontinued on December 18, 2024. +Jun 6, 2025 +gpt-4-32k-0613 Historical price $60.00 / 1M input tokens + $120 / 1M output tokens +gpt-4o +Jun 6, 2024 -See the Assistants API v2 beta migration guide to learn more about how to migrate your tool usage to the latest version of the Assistants API. +Jun 6, 2025 +gpt-4-32k-0314 Historical price $60.00 / 1M input tokens + $120 / 1M output tokens +gpt-4o +Jun 13, 2023 -Shutdown date -Model / system -Recommended replacement - -2024-12-18 +Dec 18, 2024 OpenAI-Beta: assistants=v1 -OpenAI-Beta: assistants=v2 +OpenAI-Beta: assistants=v2 (migration guide) +Oct 2, 2024 -2024-08-29: Fine-tuning training on babbage-002 and davinci-002 models +Dec 6, 2024 +gpt-4-vision-preview Historical price $10.00 / 1M input tokens + $30 / 1M output tokens +gpt-4o +Jun 6, 2024 -On August 29th, 2024, we notified developers fine-tuning babbage-002 and davinci-002 that new fine-tuning training runs on these models will no longer be supported starting October 28, 2024. +Dec 6, 2024 +gpt-4-1106-vision-preview Historical price $10.00 / 1M input tokens + $30 / 1M output tokens +gpt-4o +Jun 6, 2024 -Fine-tuned models created from these base models are not affected by this deprecation, but you will no longer be able to create new fine-tuned versions with these models. - -Shutdown date -Model / system -Recommended replacement - -2024-10-28 +Oct 28, 2024 New fine-tuning training on babbage-002 gpt-4o-mini +Aug 29, 2024 -2024-10-28 +Oct 28, 2024 New fine-tuning training on davinci-002 gpt-4o-mini +Aug 29, 2024 -2024-06-06: GPT-4-32K and Vision Preview models +Sep 13, 2024 +gpt-3.5-turbo-0613 Historical price $1.50 / 1M input tokens + $2.00 / 1M output tokens +gpt-3.5-turbo +Nov 6, 2023 -On June 6th, 2024, we notified developers using gpt-4-32k and gpt-4-vision-preview of their upcoming deprecations in one year and six months respectively. As of June 17, 2024, only existing users of these models will be able to continue using them. - -Shutdown date -Deprecated model -Deprecated model price -Recommended replacement - -2025-06-06 -gpt-4-32k -$60.00 / 1M input tokens + $120 / 1M output tokens -gpt-4o - -2025-06-06 -gpt-4-32k-0613 -$60.00 / 1M input tokens + $120 / 1M output tokens -gpt-4o - -2025-06-06 -gpt-4-32k-0314 -$60.00 / 1M input tokens + $120 / 1M output tokens -gpt-4o - -2024-12-06 -gpt-4-vision-preview -$10.00 / 1M input tokens + $30 / 1M output tokens -gpt-4o - -2024-12-06 -gpt-4-1106-vision-preview -$10.00 / 1M input tokens + $30 / 1M output tokens -gpt-4o - -2023-11-06: Chat model updates - -On November 6th, 2023, we announced the release of an updated GPT-3.5-Turbo model (which now comes by default with 16k context) along with deprecation of gpt-3.5-turbo-0613 and gpt-3.5-turbo-16k-0613. As of June 17, 2024, only existing users of these models will be able to continue using them. - -Shutdown date -Deprecated model -Deprecated model price -Recommended replacement - -2024-09-13 -gpt-3.5-turbo-0613 -$1.50 / 1M input tokens + $2.00 / 1M output tokens +Sep 13, 2024 +gpt-3.5-turbo-16k-0613 Historical price $3.00 / 1M input tokens + $4.00 / 1M output tokens gpt-3.5-turbo +Nov 6, 2023 -2024-09-13 -gpt-3.5-turbo-16k-0613 -$3.00 / 1M input tokens + $4.00 / 1M output tokens +Sep 13, 2024 +gpt-3.5-turbo-0301 Historical price $15.00 / 1M input tokens + $20.00 / 1M output tokens gpt-3.5-turbo +Jun 13, 2023 -Fine-tuned models created from these base models are not affected by this deprecation, but you will no longer be able to create new fine-tuned versions with these models. +Jun 13, 2024 Earliest estimate +gpt-4-0314 Historical price $30.00 / 1M input tokens + $60.00 / 1M output tokens +gpt-4o +Jun 13, 2023 -2023-08-22: Fine-tunes endpoint - -On August 22nd, 2023, we announced the new fine-tuning API (/v1/fine_tuning/jobs) and that the original /v1/fine-tunes API along with legacy models (including those fine-tuned with the /v1/fine-tunes API) will be shut down on January 04, 2024. This means that models fine-tuned using the /v1/fine-tunes API will no longer be accessible and you would have to fine-tune new models with the updated endpoint and associated base models. - -Fine-tunes endpoint - -Shutdown date -System -Recommended replacement - -2024-01-04 +Jan 4, 2024 /v1/fine-tunes /v1/fine_tuning/jobs +Aug 22, 2023 -2023-07-06: GPT and embeddings - -On July 06, 2023, we announced the upcoming retirements of older GPT-3 and GPT-3.5 models served via the completions endpoint. We also announced the upcoming retirement of our first-generation text embedding models. They will be shut down on January 04, 2024. - -InstructGPT models - -Shutdown date -Deprecated model -Deprecated model price -Recommended replacement - -2024-01-04 -text-ada-001 -$0.40 / 1M tokens +Jan 4, 2024 +text-ada-001 Historical price $0.40 / 1M tokens gpt-3.5-turbo-instruct +Jul 6, 2023 -2024-01-04 -text-babbage-001 -$0.50 / 1M tokens +Jan 4, 2024 +text-babbage-001 Historical price $0.50 / 1M tokens gpt-3.5-turbo-instruct +Jul 6, 2023 -2024-01-04 -text-curie-001 -$2.00 / 1M tokens +Jan 4, 2024 +text-curie-001 Historical price $2.00 / 1M tokens gpt-3.5-turbo-instruct +Jul 6, 2023 -2024-01-04 -text-davinci-001 -$20.00 / 1M tokens +Jan 4, 2024 +text-davinci-001 Historical price $20.00 / 1M tokens gpt-3.5-turbo-instruct +Jul 6, 2023 -2024-01-04 -text-davinci-002 -$20.00 / 1M tokens +Jan 4, 2024 +text-davinci-002 Historical price $20.00 / 1M tokens gpt-3.5-turbo-instruct +Jul 6, 2023 -2024-01-04 -text-davinci-003 -$20.00 / 1M tokens +Jan 4, 2024 +text-davinci-003 Historical price $20.00 / 1M tokens gpt-3.5-turbo-instruct +Jul 6, 2023 -Pricing for the replacement gpt-3.5-turbo-instruct model can be found on the pricing page. - -Base GPT models - -Shutdown date -Deprecated model -Deprecated model price -Recommended replacement - -2024-01-04 -ada -$0.40 / 1M tokens +Jan 4, 2024 +ada Historical price $0.40 / 1M tokens babbage-002 +Jul 6, 2023 -2024-01-04 -babbage -$0.50 / 1M tokens +Jan 4, 2024 +babbage Historical price $0.50 / 1M tokens babbage-002 +Jul 6, 2023 -2024-01-04 -curie -$2.00 / 1M tokens +Jan 4, 2024 +curie Historical price $2.00 / 1M tokens davinci-002 +Jul 6, 2023 -2024-01-04 -davinci -$20.00 / 1M tokens +Jan 4, 2024 +davinci Historical price $20.00 / 1M tokens davinci-002 +Jul 6, 2023 -2024-01-04 -code-davinci-002 -— +Jan 4, 2024 +code-davinci-002 (base GPT models) gpt-3.5-turbo-instruct +Jul 6, 2023 -Pricing for the replacement babbage-002 and davinci-002 models can be found on the pricing page. - -Edit models & endpoint - -Shutdown date -Model / system -Recommended replacement - -2024-01-04 +Jan 4, 2024 text-davinci-edit-001 gpt-4o +Jul 6, 2023 -2024-01-04 +Jan 4, 2024 code-davinci-edit-001 gpt-4o +Jul 6, 2023 -2024-01-04 +Jan 4, 2024 /v1/edits /v1/chat/completions +Jul 6, 2023 -Fine-tuning GPT models - -Shutdown date -Deprecated model -Training price -Usage price -Recommended replacement - -2024-01-04 -ada -$0.40 / 1M tokens -$1.60 / 1M tokens +Jan 4, 2024 +Fine-tuning on ada Training price $0.40 / 1M tokens. Usage price $1.60 / 1M tokens babbage-002 +Jul 6, 2023 -2024-01-04 -babbage -$0.60 / 1M tokens -$2.40 / 1M tokens +Jan 4, 2024 +Fine-tuning on babbage Training price $0.60 / 1M tokens. Usage price $2.40 / 1M tokens babbage-002 +Jul 6, 2023 -2024-01-04 -curie -$3.00 / 1M tokens -$12.00 / 1M tokens +Jan 4, 2024 +Fine-tuning on curie Training price $3.00 / 1M tokens. Usage price $12.00 / 1M tokens davinci-002 +Jul 6, 2023 -2024-01-04 -davinci -$30.00 / 1M tokens -$120.00 / 1K tokens +Jan 4, 2024 +Fine-tuning on davinci Training price $30.00 / 1M tokens. Usage price $120.00 / 1K tokens davinci-002, gpt-3.5-turbo, gpt-4o +Jul 6, 2023 -First-generation text embedding models - -Shutdown date -Deprecated model -Deprecated model price -Recommended replacement - -2024-01-04 -text-similarity-ada-001 -$4.00 / 1M tokens +Jan 4, 2024 +text-similarity-ada-001 Historical price $4.00 / 1M tokens text-embedding-3-small +Jul 6, 2023 -2024-01-04 -text-search-ada-doc-001 -$4.00 / 1M tokens +Jan 4, 2024 +text-search-ada-doc-001 Historical price $4.00 / 1M tokens text-embedding-3-small +Jul 6, 2023 -2024-01-04 -text-search-ada-query-001 -$4.00 / 1M tokens +Jan 4, 2024 +text-search-ada-query-001 Historical price $4.00 / 1M tokens text-embedding-3-small +Jul 6, 2023 -2024-01-04 -code-search-ada-code-001 -$4.00 / 1M tokens +Jan 4, 2024 +code-search-ada-code-001 Historical price $4.00 / 1M tokens text-embedding-3-small +Jul 6, 2023 -2024-01-04 -code-search-ada-text-001 -$4.00 / 1M tokens +Jan 4, 2024 +code-search-ada-text-001 Historical price $4.00 / 1M tokens text-embedding-3-small +Jul 6, 2023 -2024-01-04 -text-similarity-babbage-001 -$5.00 / 1M tokens +Jan 4, 2024 +text-similarity-babbage-001 Historical price $5.00 / 1M tokens text-embedding-3-small +Jul 6, 2023 -2024-01-04 -text-search-babbage-doc-001 -$5.00 / 1M tokens +Jan 4, 2024 +text-search-babbage-doc-001 Historical price $5.00 / 1M tokens text-embedding-3-small +Jul 6, 2023 -2024-01-04 -text-search-babbage-query-001 -$5.00 / 1M tokens +Jan 4, 2024 +text-search-babbage-query-001 Historical price $5.00 / 1M tokens text-embedding-3-small +Jul 6, 2023 -2024-01-04 -code-search-babbage-code-001 -$5.00 / 1M tokens +Jan 4, 2024 +code-search-babbage-code-001 Historical price $5.00 / 1M tokens text-embedding-3-small +Jul 6, 2023 -2024-01-04 -code-search-babbage-text-001 -$5.00 / 1M tokens +Jan 4, 2024 +code-search-babbage-text-001 Historical price $5.00 / 1M tokens text-embedding-3-small +Jul 6, 2023 -2024-01-04 -text-similarity-curie-001 -$20.00 / 1M tokens +Jan 4, 2024 +text-similarity-curie-001 Historical price $20.00 / 1M tokens text-embedding-3-small +Jul 6, 2023 -2024-01-04 -text-search-curie-doc-001 -$20.00 / 1M tokens +Jan 4, 2024 +text-search-curie-doc-001 Historical price $20.00 / 1M tokens text-embedding-3-small +Jul 6, 2023 -2024-01-04 -text-search-curie-query-001 -$20.00 / 1M tokens +Jan 4, 2024 +text-search-curie-query-001 Historical price $20.00 / 1M tokens text-embedding-3-small +Jul 6, 2023 -2024-01-04 -text-similarity-davinci-001 -$200.00 / 1M tokens +Jan 4, 2024 +text-similarity-davinci-001 Historical price $200.00 / 1M tokens text-embedding-3-small +Jul 6, 2023 -2024-01-04 -text-search-davinci-doc-001 -$200.00 / 1M tokens +Jan 4, 2024 +text-search-davinci-doc-001 Historical price $200.00 / 1M tokens text-embedding-3-small +Jul 6, 2023 -2024-01-04 -text-search-davinci-query-001 -$200.00 / 1M tokens +Jan 4, 2024 +text-search-davinci-query-001 Historical price $200.00 / 1M tokens text-embedding-3-small +Jul 6, 2023 -2023-06-13: Updated chat models - -On June 13, 2023, we announced new chat model versions in the Function calling and other API updates blog post. The three original versions will be retired in June 2024 at the earliest. As of January 10, 2024, only existing users of these models will be able to continue using them. - -Shutdown date -Legacy model -Legacy model price -Recommended replacement - -at earliest 2024-06-13 -gpt-4-0314 -$30.00 / 1M input tokens + $60.00 / 1M output tokens +Mar 23, 2023 +code-davinci-002 (Codex models) gpt-4o +Mar 20, 2023 -Shutdown date -Deprecated model -Deprecated model price -Recommended replacement - -2024-09-13 -gpt-3.5-turbo-0301 -$15.00 / 1M input tokens + $20.00 / 1M output tokens -gpt-3.5-turbo - -2025-06-06 -gpt-4-32k-0314 -$60.00 / 1M input tokens + $120.00 / 1M output tokens -gpt-4o - -2023-03-20: Codex models - -Shutdown date -Deprecated model -Recommended replacement - -2023-03-23 -code-davinci-002 -gpt-4o - -2023-03-23 +Mar 23, 2023 code-davinci-001 gpt-4o +Mar 20, 2023 -2023-03-23 +Mar 23, 2023 code-cushman-002 gpt-4o +Mar 20, 2023 -2023-03-23 +Mar 23, 2023 code-cushman-001 gpt-4o +Mar 20, 2023 -2022-06-03: Legacy endpoints - -Shutdown date -System -Recommended replacement - -2022-12-03 +Dec 3, 2022 /v1/engines /v1/models +Jun 3, 2022 -2022-12-03 +Dec 3, 2022 /v1/search View transition guide +Jun 3, 2022 -2022-12-03 +Dec 3, 2022 /v1/classifications View transition guide +Jun 3, 2022 -2022-12-03 +Dec 3, 2022 /v1/answers -View transition guide +View transition guide +Jun 3, 2022 + +Historical notes + +Fine-tuned versions of the legacy GPT models shut down in October 2026 followed the same shutdown schedule as their underlying base models. + +The codex-mini-latest shutdown also ended support for the legacy local shell tool. For new integrations, use the shell tool. + +The Assistants API notice followed the release of the Responses API in March 2025. We first announced plans to retire the Assistants API v1 beta when we released v2 in April 2024. + +The October 2024 shutdown for fine-tuning training on babbage-002 and davinci-002 applied to creating new fine-tuned models. Existing fine-tuned models were unaffected by that change. + +The June 6, 2024 notice reconfirmed the retirement of gpt-4-32k-0314. Starting June 17, 2024, access to the GPT-4-32K and Vision Preview models and the GPT-3.5 Turbo snapshots announced in November 2023 was limited to existing users. Existing fine-tuned models from those GPT-3.5 Turbo snapshots were unaffected by that shutdown. + +The legacy fine-tunes endpoint shutdown also removed access to models trained with that endpoint. Developers had to train new models through the updated fine-tuning API. + +The July 2023 announcement covered older GPT-3 and GPT-3.5 models served through the completions endpoint and first-generation text embedding models. See the pricing page for current model pricing. + +The June 2023 announcement gave an earliest retirement date of June 13, 2024 for the original chat models. Starting January 10, 2024, access was limited to existing users. See the March 2026 shutdown notice for the final shutdown date of gpt-4-0314.
HOW IT WAS JUDGED
Triage signals below are model-reported assertions, not independent arithmetic verification. A wrong figure in them has been corrected (config/corrected-text.yaml); the model's wording is kept, struck through, under the original text, and in data.json under original.triage.
| triage verdict | MATERIAL at 0.95, needed 0.45 |
|---|---|
| triage reasoning | Multiple future model shutdowns with specific dates, restated in a new table; no new deprecations in this change; engineering teams must plan migrations. |
| signals | page restructured from announcement-driven to table-driven format · multiple future shutdown dates present: Dec 1 2026, Dec 11 2026, Jan 6 2027, Jan 14 2027, Jan 20 2027, Feb 1 2027, Feb 10 2027, Feb 26 2027, Apr 1 2027 · models carried into the new table, all already listed on the old page: gpt-image-1-mini, gpt-image-1.5, chatgpt-image-latest with Dec 1 2026 shutdown; gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro, o3, o3-pro with Dec 11 2026 shutdown · feature deprecations carried into the new table, all already listed on the old page: /v1/prompts, Evals dashboard, Agent Builder, self-serve fine-tuning job creation · notice dates documented: Jun 2 2026 for image models, Jun 11 2026 for GPT-5/o3, Oct 1 2026 for text-to-speech and Codex variants · replacement models specified: gpt-6.1-sol, gpt-6.1-terra, gpt-6-luna for upcoming deprecations · past deprecations section reorganized with historical notes added · removed: blog post notification language, detailed announcement sections with dates · added: lifecycle state definitions (Active, Deprecated, Shutdown), programmatic monitoring guidance moved to 'Best practices' |
| suppression | — |
| triage model | anthropic/claude-haiku-4.5 ($0.00000) |
| writer model | anthropic/claude-sonnet-4.5 ($0.00000) |