{"slug": "openai-agent-builder-is-being-deprecated", "title": "OpenAI Agent Builder Is Being Deprecated", "summary": "OpenAI deprecated its Agent Builder tool on June 3, 2026, notifying developers that the product will be shut down by November 30, 2026. The company is directing users to migrate their agent configurations to alternative solutions as part of its ongoing platform updates.", "body_md": "## Overview\n\nAs 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](https://openai.com/blog) for larger changes.\n\nThis page lists all API deprecations, along with recommended replacements.\n\n## Model deprecation notice periods\n\nWe 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.\n\nUnless safety or compliance concerns require a faster timeline, we provide the following minimum notice periods before model retirement:\n\n**Generally available models:** At least 6 months.**Specialized variants of generally available models:** At least 3 months. Examples include chat variants such as`gpt-5.1-chat-latest`\n\n, Codex variants such as`gpt-5.3-codex`\n\n, and deep research variants such as`o3-deep-research`\n\n.**Preview models:** Preview models, identified by`preview`\n\nin the model name, may be retired with much shorter notice, such as 2 weeks. Examples include`computer-use-preview`\n\nand`gpt-4o-audio-preview`\n\n. We don’t recommend using preview models for business-critical production workloads unless you can migrate on short notice.\n\nIf safety or compliance concerns require us to retire a model sooner, we will provide as much notice as reasonably possible.\n\nThese 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](https://openai.com/contact-sales/).\n\n## Deprecation vs. legacy\n\nWe 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.\n\nWe use the terms “sunset” and “shut down” interchangeably to mean a model or endpoint is no longer accessible.\n\nWe 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.\n\n## Upcoming deprecations\n\nUpcoming deprecations are listed below, with the most recent announcements at the top.\n\n### 2026-06-03: Reusable prompts\n\nOn June 3, 2026, we notified developers using reusable prompts in the dashboard and API that reusable prompt objects are being deprecated.\n\n| Date | Update |\n|---|---|\n| June 3, 2026 | Deprecation announced and prompt creation de-emphasized in the platform. |\n| Nov 30, 2026 | The `v1/prompts` API and reusable prompt objects are scheduled to shut down. |\n\nTo migrate, move reusable prompt content into your application code. See [Migrate from prompt objects](/api/docs/guides/prompting/migrate-from-prompt-object).\n\n### 2026-06-03: Evals platform\n\nOn June 3, 2026, we notified developers using the Evals platform that the product is being deprecated.\n\n| Date | Update |\n|---|---|\n| June 3, 2026 | Deprecation announced for the Evals platform. |\n| Oct 31, 2026 | Existing evals become read-only. |\n| Nov 30, 2026 | The Evals dashboard and API are scheduled to shut down. |\n\nGraders documented for eval workflows are part of this transition. Fine-tuning-related timelines remain covered in the self-serve fine-tuning section below.\n\nSee [Moving from OpenAI Evals to Promptfoo](/cookbook/examples/evaluation/moving-from-openai-evals-to-promptfoo) for a migration path.\n\n### 2026-06-03: Agent Builder\n\nOn June 3, 2026, we notified developers using Agent Builder that the product is being deprecated. ChatKit remains available.\n\n| Date | Update |\n|---|---|\n| June 3, 2026 | Deprecation announced for Agent Builder. |\n| Nov 30, 2026 | Agent Builder is scheduled to shut down. |\n\nSee [Migrate from Agent Builder](/api/docs/guides/agent-builder/migrate-from-agent-builder) to continue with the Agents SDK or ChatGPT Workspace Agents.\n\n### 2026-06-02: GPT Image model deprecations\n\nOn June 2, 2026, we notified developers using older GPT Image models of their deprecation and removal from the API on December 1, 2026.\n\n| Shutdown date | Model / system | Recommended replacement |\n|---|---|---|\n| Dec 1, 2026 | `gpt-image-1-mini` | `gpt-image-2` |\n| Dec 1, 2026 | `gpt-image-1.5` | `gpt-image-2` |\n| Dec 1, 2026 | `chatgpt-image-latest` | `gpt-image-2` |\n\n### 2026-05-08: gpt-5.2-chat-latest and gpt-5.3-chat-latest model snapshots\n\nOn May 8th, 2026, we notified developers using `gpt-5.2-chat-latest`\n\nand `gpt-5.3-chat-latest`\n\nmodel snapshots of their deprecation and removal from the API.\n\n| Shutdown date | Model / system | Recommended replacement |\n|---|---|---|\n| Aug 10, 2026 | `gpt-5.2-chat-latest` | `gpt-5.5` |\n| Aug 10, 2026 | `gpt-5.3-chat-latest` | `gpt-5.5` |\n\n### Update to OpenAI’s self-serve fine-tuning\n\nOn May 7th, 2026, we notified developers using OpenAI’s self-serve fine-tuning platform of updates to availability.\n\nInference on fine-tuned models will continue to be available until the base models are deprecated.\n\n| Date | Update |\n|---|---|\n| May 7, 2026 | Creating fine-tuning jobs or training is not available to organizations that have not previously run fine-tuning. |\n| July 2, 2026 | Creating fine-tuning jobs is no longer available to organizations that have not run inference on a fine-tuned model in the past 60 days. |\n| Jan 6, 2027 | Active existing customers will no longer be able to create new fine-tuning jobs on this date. Inference on fine-tuned models will be disabled only when the underlying base model is deprecated. |\n\n### 2026-04-22: Legacy GPT model snapshots\n\nTo improve reliability and make it easier for developers to choose the right models, we are deprecating a set of older OpenAI models. Access to these models will be shut down on the dates below.\n\n| Shutdown date | Model snapshot | Substitute model |\n|---|---|---|\n| 2026-07-23 | `computer-use-preview-2025-03-11` | `computer-use-preview` | `gpt-5.4-mini` |\n| 2026-07-23 | `gpt-4o-mini-search-preview-2025-03-11` | `gpt-5.4-mini` |\n| 2026-07-23 | `gpt-4o-mini-tts-2025-03-20` | `gpt-4o-mini-tts-2025-12-15` |\n| 2026-07-23 | `gpt-4o-search-preview-2025-03-11` | `gpt-5.4-mini` |\n| 2026-07-23 | `gpt-5-chat-latest` | `gpt-5.5` |\n| 2026-07-23 | `gpt-5-codex` | `gpt-5.5` |\n| 2026-07-23 | `gpt-5.1-chat-latest` | `gpt-5.5` |\n| 2026-07-23 | `gpt-5.1-codex` | `gpt-5.5` |\n| 2026-07-23 | `gpt-5.1-codex-max` | `gpt-5.5` |\n| 2026-07-23 | `gpt-5.1-codex-mini` | `gpt-5.4-mini` |\n| 2026-07-23 | `gpt-audio-mini-2025-10-06` | `gpt-audio-1.5` |\n| 2026-07-23 | `gpt-realtime-mini-2025-10-06` | `gpt-realtime-mini` |\n| 2026-07-23 | `o3-deep-research-2025-06-26` | `o3-deep-research` | `gpt-5.5-pro` |\n| 2026-07-23 | `o4-mini-deep-research-2025-06-26` | `o4-mini-deep-research` | `gpt-5.5-pro` |\n| 2026-07-23 | `gpt-5.2-codex` | `gpt-5.5` |\n| 2026-10-23 | `gpt-3.5-turbo-0125` | `gpt-3.5-turbo` , `gpt-3.5-turbo-completions` | `gpt-5.4-mini` |\n| 2026-10-23 | `gpt-4-0613` | `gpt-4` , `gpt-4-0613-completions` , `gpt-4-completions` | `gpt-5.5` |\n| 2026-10-23 | `gpt-4-1106-preview` | `gpt-5.5` |\n| 2026-10-23 | `gpt-4-turbo` | `gpt-4-turbo-2024-04-09` , `gpt-4-turbo-completions` | `gpt-5.5` |\n| 2026-10-23 | `gpt-4.1-nano` | `gpt-4.1-nano-2025-04-14` | `gpt-5.4-nano` |\n| 2026-10-23 | `gpt-4o-2024-05-13` | `gpt-5.5` |\n| 2026-10-23 | `gpt-image-1` | `gpt-image-2` |\n| 2026-10-23 | `o1-2024-12-17` | `o1` | `gpt-5.5` |\n| 2026-10-23 | `o1-pro-2025-03-19` | `o1-pro` | `gpt-5.5-pro` |\n| 2026-10-23 | `o3-mini-2025-01-31` | `o3-mini` | `gpt-5.5` |\n| 2026-10-23 | `ft-o4-mini-2025-04-16` | `gpt-5.4-mini` |\n| 2026-10-23 | `o4-mini-2025-04-16` | `o4-mini` | `gpt-5.4-mini` |\n\nWe are also removing fine-tuned versions as below:\n\n| Shutdown date | Model snapshot | Recommended replacement base model |\n|---|---|---|\n| 2026-10-23 | `ft-gpt-3.5-turbo` | `gpt-5.4-mini` |\n| 2026-10-23 | `ft-gpt-4` | `gpt-5.5` |\n| 2026-10-23 | `ft-gpt-4.1-nano-2025-04-14` | `gpt-5.4-nano` |\n| 2026-10-23 | `ft-babbage-002` | `gpt-5.4-mini` |\n| 2026-10-23 | `ft-davinci-002` | `gpt-5.4-mini` |\n\n### 2026-03-24: Sora 2 video generation models and Videos API\n\nOn 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.\n\n| Shutdown date | Model / system | Recommended replacement |\n|---|---|---|\n| 2026-09-24 | Videos API | --- |\n| 2026-09-24 | `sora-2` | --- |\n| 2026-09-24 | `sora-2-pro` | --- |\n| 2026-09-24 | `sora-2-2025-10-06` | --- |\n| 2026-09-24 | `sora-2-2025-12-08` | --- |\n| 2026-09-24 | `sora-2-pro-2025-10-06` | --- |\n\n### 2025-11-14: DALL·E model snapshots\n\nOn November 14th, 2025, we notified developers using DALL·E model snapshots of their deprecation and removal from the API on May 12, 2026.\n\n| Shutdown date | Model / system | Recommended replacement |\n|---|---|---|\n| 2026-05-12 | `dall-e-2` | `gpt-image-2` , `gpt-image-1` , or `gpt-image-1-mini` |\n| 2026-05-12 | `dall-e-3` | `gpt-image-2` , `gpt-image-1` , or `gpt-image-1-mini` |\n\n### 2025-09-26: Legacy GPT model snapshots\n\nTo improve reliability and make it easier for developers to choose the right models, we are deprecating a set of older OpenAI models with declining usage over the next six to twelve months. Access to these models will be shut down on the dates below.\n\n| Shutdown date | Model / system | Recommended replacement |\n|---|---|---|\n| 2026‑03‑26 | `gpt-4-0314` | `gpt-5` or `gpt-4.1*` |\n| 2026‑03‑26 | `gpt-4-1106-preview` | `gpt-5` or `gpt-4.1*` |\n| 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*` |\n| 2026-09-28 | `gpt-3.5-turbo-instruct` | `gpt-5.4-mini` or `gpt-5-mini` |\n| 2026-09-28 | `babbage-002` | `gpt-5.4-mini` or `gpt-5-mini` |\n| 2026-09-28 | `davinci-002` | `gpt-5.4-mini` or `gpt-5-mini` |\n| 2026-09-28 | `gpt-3.5-turbo-1106` | `gpt-5.4-mini` or `gpt-5-mini` |\n\n*For tasks that are especially latency sensitive and don’t require reasoning\n\n### 2025-09-15: Realtime API Beta\n\nThe Realtime API Beta was deprecated and removed from the API on May 12, 2026.\n\nThere are a few key differences between the interfaces in the Realtime beta API and the released GA API. See [the migration guide](/api/docs/guides/realtime#beta-to-ga-migration) for the current GA interface and related Realtime docs.\n\n| Shutdown date | Model / system | Recommended replacement |\n|---|---|---|\n| 2026‑05‑12 | OpenAI-Beta: realtime=v1 | Realtime API |\n\n### 2025-08-20: Assistants API\n\nOn 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.\n\nWhen we released the [Responses API](/api/docs/api-reference/responses/create) in [March 2025](/api/docs/changelog), we announced plans to bring all Assistants API features to the easier to use Responses API, with a sunset date in 2026.\n\nSee the Assistants to Conversations [migration guide](/api/docs/assistants/migration) to learn more about how to migrate your current integration to the Responses API and Conversations API.\n\n| Shutdown date | Model / system | Recommended replacement |\n|---|---|---|\n| 2026‑08‑26 | Assistants API | Responses API and Conversations API |\n\n### 2025-09-15: gpt-4o-realtime-preview models\n\nIn September, 2025, we notified developers using gpt-4o-realtime-preview models of their deprecation and removal from the API in six months.\n\n| Shutdown date | Model / system | Recommended replacement |\n|---|---|---|\n| 2026-05-07 | gpt-4o-realtime-preview | gpt-realtime-1.5 |\n| 2026-05-07 | gpt-4o-realtime-preview-2025-06-03 | gpt-realtime-1.5 |\n| 2026-05-07 | gpt-4o-realtime-preview-2024-12-17 | gpt-realtime-1.5 |\n| 2026-05-07 | gpt-4o-mini-realtime-preview | gpt-realtime-mini |\n| 2026-05-07 | gpt-4o-audio-preview | gpt-audio-1.5 |\n| 2026-05-07 | gpt-4o-mini-audio-preview | gpt-audio-mini |\n\n## Past deprecations\n\nPast deprecations are listed below, with the most recent announcements at the top.\n\n### 2025-11-18: chatgpt-4o-latest snapshot\n\nOn November 18th, 2025, we notified developers using `chatgpt-4o-latest`\n\nmodel snapshot of its deprecation and removal from the API on February 17, 2026.\n\n| Shutdown date | Model / system | Recommended replacement |\n|---|---|---|\n| 2026-02-17 | `chatgpt-4o-latest` | `gpt-5.1-chat-latest` |\n\n### 2025-11-17: codex-mini-latest model snapshot\n\nOn November 17th, 2025, we notified developers using `codex-mini-latest`\n\nmodel 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`\n\n. For new use cases, please use our latest shell tool.\n\n| Shutdown date | Model / system | Recommended replacement |\n|---|---|---|\n| 2026-02-12 | `codex-mini-latest` | `gpt-5-codex-mini` |\n\n### 2025-06-10: gpt-4o-realtime-preview-2024-10-01\n\nOn 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.\n\n| Shutdown date | Model / system | Recommended replacement |\n|---|---|---|\n| 2025-10-10 | gpt-4o-realtime-preview-2024-10-01 | gpt-realtime-1.5 |\n\n### 2025-06-10: gpt-4o-audio-preview-2024-10-01\n\nOn June 10th, 2025, we notified developers using `gpt-4o-audio-preview-2024-10-01`\n\nof its deprecation and removal from the API in three months.\n\n| Shutdown date | Model / system | Recommended replacement |\n|---|---|---|\n| 2025-10-10 | `gpt-4o-audio-preview-2024-10-01` | `gpt-audio-1.5` |\n\n### 2025-04-28: text-moderation\n\nOn April 28th, 2025, we notified developers using `text-moderation`\n\nof its deprecation and removal from the API in six months.\n\n| Shutdown date | Model / system | Recommended replacement |\n|---|---|---|\n| 2025-10-27 | `text-moderation-007` | `omni-moderation` |\n| 2025-10-27 | `text-moderation-stable` | `omni-moderation` |\n| 2025-10-27 | `text-moderation-latest` | `omni-moderation` |\n\n### 2025-04-28: o1-preview and o1-mini\n\nOn April 28th, 2025, we notified developers using `o1-preview`\n\nand `o1-mini`\n\nof their deprecations and removal from the API in three months and six months respectively.\n\n| Shutdown date | Model / system | Recommended replacement |\n|---|---|---|\n| 2025-07-28 | `o1-preview` | `o3` |\n| 2025-10-27 | `o1-mini` | `o4-mini` |\n\n### 2025-04-14: GPT-4.5-preview\n\nOn April 14th, 2025, we notified developers that the `gpt-4.5-preview`\n\nmodel is deprecated and will be removed from the API in the coming months.\n\n| Shutdown date | Model / system | Recommended replacement |\n|---|---|---|\n| 2025-07-14 | `gpt-4.5-preview` | `gpt-4.1` |\n\n### 2024-10-02: Assistants API beta v1\n\nIn [April 2024](/api/docs/assistants/whats-new) 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.\n\nSee the Assistants API v2 beta [migration guide](/api/docs/assistants/migration) to learn more about how to migrate your tool usage to the latest version of the Assistants API.\n\n| Shutdown date | Model / system | Recommended replacement |\n|---|---|---|\n| 2024-12-18 | OpenAI-Beta: assistants=v1 | OpenAI-Beta: assistants=v2 |\n\n### 2024-08-29: Fine-tuning training on babbage-002 and davinci-002 models\n\nOn August 29th, 2024, we notified developers fine-tuning `babbage-002`\n\nand `davinci-002`\n\nthat new fine-tuning training runs on these models will no longer be supported starting October 28, 2024.\n\nFine-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.\n\n| Shutdown date | Model / system | Recommended replacement |\n|---|---|---|\n| 2024-10-28 | New fine-tuning training on `babbage-002` | `gpt-4o-mini` |\n| 2024-10-28 | New fine-tuning training on `davinci-002` | `gpt-4o-mini` |\n\n### 2024-06-06: GPT-4-32K and Vision Preview models\n\nOn June 6th, 2024, we notified developers using `gpt-4-32k`\n\nand `gpt-4-vision-preview`\n\nof 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.\n\n| Shutdown date | Deprecated model | Deprecated model price | Recommended replacement |\n|---|---|---|---|\n| 2025-06-06 | `gpt-4-32k` | $60.00 / 1M input tokens + $120 / 1M output tokens | `gpt-4o` |\n| 2025-06-06 | `gpt-4-32k-0613` | $60.00 / 1M input tokens + $120 / 1M output tokens | `gpt-4o` |\n| 2025-06-06 | `gpt-4-32k-0314` | $60.00 / 1M input tokens + $120 / 1M output tokens | `gpt-4o` |\n| 2024-12-06 | `gpt-4-vision-preview` | $10.00 / 1M input tokens + $30 / 1M output tokens | `gpt-4o` |\n| 2024-12-06 | `gpt-4-1106-vision-preview` | $10.00 / 1M input tokens + $30 / 1M output tokens | `gpt-4o` |\n\n### 2023-11-06: Chat model updates\n\nOn November 6th, 2023, we [announced](https://openai.com/blog/new-models-and-developer-products-announced-at-devday) 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`\n\nand ` gpt-3.5-turbo-16k-0613`\n\n. As of June 17, 2024, only existing users of these models will be able to continue using them.\n\n| Shutdown date | Deprecated model | Deprecated model price | Recommended replacement |\n|---|---|---|---|\n| 2024-09-13 | `gpt-3.5-turbo-0613` | $1.50 / 1M input tokens + $2.00 / 1M output tokens | `gpt-3.5-turbo` |\n| 2024-09-13 | `gpt-3.5-turbo-16k-0613` | $3.00 / 1M input tokens + $4.00 / 1M output tokens | `gpt-3.5-turbo` |\n\nFine-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.\n\n### 2023-08-22: Fine-tunes endpoint\n\nOn August 22nd, 2023, we [announced](https://openai.com/blog/gpt-3-5-turbo-fine-tuning-and-api-updates) the new fine-tuning API (`/v1/fine_tuning/jobs`\n\n) and that the original `/v1/fine-tunes`\n\nAPI along with legacy models (including those fine-tuned with the `/v1/fine-tunes`\n\nAPI) will be shut down on January 04, 2024. This means that models fine-tuned using the `/v1/fine-tunes`\n\nAPI will no longer be accessible and you would have to fine-tune new models with the updated endpoint and associated base models.\n\n#### Fine-tunes endpoint\n\n| Shutdown date | System | Recommended replacement |\n|---|---|---|\n| 2024-01-04 | `/v1/fine-tunes` | `/v1/fine_tuning/jobs` |\n\n### 2023-07-06: GPT and embeddings\n\nOn July 06, 2023, we [announced](https://openai.com/blog/gpt-4-api-general-availability) 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.\n\n#### InstructGPT models\n\n| Shutdown date | Deprecated model | Deprecated model price | Recommended replacement |\n|---|---|---|---|\n| 2024-01-04 | `text-ada-001` | $0.40 / 1M tokens | `gpt-3.5-turbo-instruct` |\n| 2024-01-04 | `text-babbage-001` | $0.50 / 1M tokens | `gpt-3.5-turbo-instruct` |\n| 2024-01-04 | `text-curie-001` | $2.00 / 1M tokens | `gpt-3.5-turbo-instruct` |\n| 2024-01-04 | `text-davinci-001` | $20.00 / 1M tokens | `gpt-3.5-turbo-instruct` |\n| 2024-01-04 | `text-davinci-002` | $20.00 / 1M tokens | `gpt-3.5-turbo-instruct` |\n| 2024-01-04 | `text-davinci-003` | $20.00 / 1M tokens | `gpt-3.5-turbo-instruct` |\n\nPricing for the replacement `gpt-3.5-turbo-instruct`\n\nmodel can be found on the [pricing page](https://openai.com/api/pricing).\n\n#### Base GPT models\n\n| Shutdown date | Deprecated model | Deprecated model price | Recommended replacement |\n|---|---|---|---|\n| 2024-01-04 | `ada` | $0.40 / 1M tokens | `babbage-002` |\n| 2024-01-04 | `babbage` | $0.50 / 1M tokens | `babbage-002` |\n| 2024-01-04 | `curie` | $2.00 / 1M tokens | `davinci-002` |\n| 2024-01-04 | `davinci` | $20.00 / 1M tokens | `davinci-002` |\n| 2024-01-04 | `code-davinci-002` | --- | `gpt-3.5-turbo-instruct` |\n\nPricing for the replacement `babbage-002`\n\nand `davinci-002`\n\nmodels can be found on the [pricing page](https://openai.com/api/pricing).\n\n#### Edit models & endpoint\n\n| Shutdown date | Model / system | Recommended replacement |\n|---|---|---|\n| 2024-01-04 | `text-davinci-edit-001` | `gpt-4o` |\n| 2024-01-04 | `code-davinci-edit-001` | `gpt-4o` |\n| 2024-01-04 | `/v1/edits` | `/v1/chat/completions` |\n\n#### Fine-tuning GPT models\n\n| Shutdown date | Deprecated model | Training price | Usage price | Recommended replacement |\n|---|---|---|---|---|\n| 2024-01-04 | `ada` | $0.40 / 1M tokens | $1.60 / 1M tokens | `babbage-002` |\n| 2024-01-04 | `babbage` | $0.60 / 1M tokens | $2.40 / 1M tokens | `babbage-002` |\n| 2024-01-04 | `curie` | $3.00 / 1M tokens | $12.00 / 1M tokens | `davinci-002` |\n| 2024-01-04 | `davinci` | $30.00 / 1M tokens | $120.00 / 1K tokens | `davinci-002` , `gpt-3.5-turbo` , `gpt-4o` |\n\n#### First-generation text embedding models\n\n| Shutdown date | Deprecated model | Deprecated model price | Recommended replacement |\n|---|---|---|---|\n| 2024-01-04 | `text-similarity-ada-001` | $4.00 / 1M tokens | `text-embedding-3-small` |\n| 2024-01-04 | `text-search-ada-doc-001` | $4.00 / 1M tokens | `text-embedding-3-small` |\n| 2024-01-04 | `text-search-ada-query-001` | $4.00 / 1M tokens | `text-embedding-3-small` |\n| 2024-01-04 | `code-search-ada-code-001` | $4.00 / 1M tokens | `text-embedding-3-small` |\n| 2024-01-04 | `code-search-ada-text-001` | $4.00 / 1M tokens | `text-embedding-3-small` |\n| 2024-01-04 | `text-similarity-babbage-001` | $5.00 / 1M tokens | `text-embedding-3-small` |\n| 2024-01-04 | `text-search-babbage-doc-001` | $5.00 / 1M tokens | `text-embedding-3-small` |\n| 2024-01-04 | `text-search-babbage-query-001` | $5.00 / 1M tokens | `text-embedding-3-small` |\n| 2024-01-04 | `code-search-babbage-code-001` | $5.00 / 1M tokens | `text-embedding-3-small` |\n| 2024-01-04 | `code-search-babbage-text-001` | $5.00 / 1M tokens | `text-embedding-3-small` |\n| 2024-01-04 | `text-similarity-curie-001` | $20.00 / 1M tokens | `text-embedding-3-small` |\n| 2024-01-04 | `text-search-curie-doc-001` | $20.00 / 1M tokens | `text-embedding-3-small` |\n| 2024-01-04 | `text-search-curie-query-001` | $20.00 / 1M tokens | `text-embedding-3-small` |\n| 2024-01-04 | `text-similarity-davinci-001` | $200.00 / 1M tokens | `text-embedding-3-small` |\n| 2024-01-04 | `text-search-davinci-doc-001` | $200.00 / 1M tokens | `text-embedding-3-small` |\n| 2024-01-04 | `text-search-davinci-query-001` | $200.00 / 1M tokens | `text-embedding-3-small` |\n\n### 2023-06-13: Updated chat models\n\nOn June 13, 2023, we announced new chat model versions in the [Function calling and other API updates](https://openai.com/blog/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.\n\n| Shutdown date | Legacy model | Legacy model price | Recommended replacement |\n|---|---|---|---|\n| at earliest 2024-06-13 | `gpt-4-0314` | $30.00 / 1M input tokens + $60.00 / 1M output tokens | `gpt-4o` |\n\n| Shutdown date | Deprecated model | Deprecated model price | Recommended replacement |\n|---|---|---|---|\n| 2024-09-13 | `gpt-3.5-turbo-0301` | $15.00 / 1M input tokens + $20.00 / 1M output tokens | `gpt-3.5-turbo` |\n| 2025-06-06 | `gpt-4-32k-0314` | $60.00 / 1M input tokens + $120.00 / 1M output tokens | `gpt-4o` |\n\n### 2023-03-20: Codex models\n\n| Shutdown date | Deprecated model | Recommended replacement |\n|---|---|---|\n| 2023-03-23 | `code-davinci-002` | `gpt-4o` |\n| 2023-03-23 | `code-davinci-001` | `gpt-4o` |\n| 2023-03-23 | `code-cushman-002` | `gpt-4o` |\n| 2023-03-23 | `code-cushman-001` | `gpt-4o` |\n\n### 2022-06-03: Legacy endpoints\n\n| Shutdown date | System | Recommended replacement |\n|---|---|---|\n| 2022-12-03 | `/v1/engines` |\n|\n\n`/v1/search`\n\n[View transition guide](https://help.openai.com/en/articles/6272952-search-transition-guide)`/v1/classifications`\n\n[View transition guide](https://help.openai.com/en/articles/6272941-classifications-transition-guide)`/v1/answers`", "url": "https://wpnews.pro/news/openai-agent-builder-is-being-deprecated", "canonical_source": "https://developers.openai.com/api/docs/deprecations", "published_at": "2026-06-03 23:57:16+00:00", "updated_at": "2026-06-04 00:15:40.385059+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products", "ai-tools", "ai-safety"], "entities": ["OpenAI"], "alternates": {"html": "https://wpnews.pro/news/openai-agent-builder-is-being-deprecated", "markdown": "https://wpnews.pro/news/openai-agent-builder-is-being-deprecated.md", "text": "https://wpnews.pro/news/openai-agent-builder-is-being-deprecated.txt", "jsonld": "https://wpnews.pro/news/openai-agent-builder-is-being-deprecated.jsonld"}}